specification: API Commons MCP Server
specificationVersion: '0.1'
provider: LaunchDarkly
providerId: launchdarkly
name: LaunchDarkly MCP Server
generated: '2026-08-27'
method: searched
status: published
source: https://launchdarkly.com/docs/home/getting-started/mcp
docs:
- https://launchdarkly.com/docs/home/getting-started/mcp
- https://launchdarkly.com/docs/home/getting-started/mcp-hosted
- https://launchdarkly.com/docs/home/getting-started/mcp-local
description: LaunchDarkly operates a first-party hosted MCP server covering feature management, AgentControl
  and observability, and also publishes a local stdio server for the federal and EU instances where the
  hosted server is not available. Both are official.
deployment:
  mode: both
  endpoint: https://mcp.launchdarkly.com/mcp/launchdarkly
  transport: streamable-http
  install: npx -y --package @launchdarkly/mcp-server -- mcp start --api-key <LAUNCHDARKLY_API_TOKEN>
  package: https://www.npmjs.com/package/@launchdarkly/mcp-server
  auth: oauth
  verified: probed
  note: Remote and local are DIFFERENT products here, not two ways to get the same thing. The hosted endpoint
    is OAuth and reachable by an agent with no local install; the npx package is stdio, takes a static
    API access token, and is the only option on the federal (app.launchdarkly.us) and EU (app.eu.launchdarkly.com)
    instances, which the docs state do not support the hosted server.
evidence:
- probe: POST tools/list (anonymous)
  url: https://mcp.launchdarkly.com/mcp/launchdarkly
  http_status: 401
  result: '{"error":{"code":-32001,"message":"unauthorized access"}} with WWW-Authenticate: Bearer resource_metadata="https://mcp.launchdarkly.com/.well-known/oauth-protected-resource/mcp/launchdarkly"'
  checked: '2026-08-27'
- probe: GET /.well-known/oauth-protected-resource/mcp/launchdarkly
  url: https://mcp.launchdarkly.com/.well-known/oauth-protected-resource/mcp/launchdarkly
  http_status: 200
  result: RFC 9728 protected-resource metadata; saved to well-known/launchdarkly-mcp-oauth-protected-resource.json
  checked: '2026-08-27'
- probe: GET /.well-known/oauth-authorization-server
  url: https://app.launchdarkly.com/.well-known/oauth-authorization-server
  http_status: 200
  result: 'RFC 8414 metadata: DCR at /trust/oauth/register/dcr, PKCE S256, scopes reader/writer/observability/offline_access'
  checked: '2026-08-27'
- probe: GET install page
  url: https://mcp.launchdarkly.com/mcp/launchdarkly/install
  http_status: 200
  result: Provider-published page listing all 125 tools with descriptions, required inputs and MCP annotations
  checked: '2026-08-27'
authentication:
  hosted:
    type: oauth2
    flow: authorization_code + PKCE (S256)
    authorization_endpoint: https://app.launchdarkly.com/trust/oauth/authorize
    token_endpoint: https://app.launchdarkly.com/trust/oauth/token
    dynamic_client_registration: https://app.launchdarkly.com/trust/oauth/register/dcr
    scopes:
    - reader
    - writer
    - observability
    - offline_access
  local:
    type: api-key
    parameter: --api-key
    credential: LaunchDarkly personal or service access token
    recommended_role: Writer base role, or a custom role granting all actions on proj/*:env/*:flag/* and
      proj/*:env/*:aiconfig/*
    warning: The provider explicitly warns that putting the token in the client config file risks leaking
      it into the conversation, and recommends an environment variable instead.
tools:
  count: 125
  source: https://mcp.launchdarkly.com/mcp/launchdarkly/install
  method: searched
  note: Names, one-line summaries, required inputs and MCP annotations are taken verbatim from the provider-published
    install page. Full inputSchemas require an authenticated tools/list and are NOT reproduced here —
    see mcp/launchdarkly-tool-crosswalk.yml for the REST operations that carry the equivalent parameter
    definitions.
  by_category:
    observability: 21
    other: 3
    account: 14
    feature-management: 29
    agentcontrol: 45
    experimentation: 13
  annotation_counts:
    Read-only: 65
    Idempotent: 78
    Destructive: 26
    Open-world: 1
  inventory:
  - tool: get-session-timestamp-event-chunk-url
    category: observability
    summary: Get a signed download URL for the rrweb event chunk covering a specific timestamp within
      a session.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - projectKey
    - sessionSecureId
    - timestamp
  - tool: get-session-event-chunk-url
    category: observability
    summary: Get a signed download URL for one rrweb event chunk of a session.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - index
    - projectKey
    - sessionSecureId
  - tool: get-session-event-chunks
    category: observability
    summary: List the rrweb event chunks recorded for a session.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - projectKey
    - sessionSecureId
  - tool: query-service-map
    category: observability
    summary: Query the service dependency map (service map) for a project.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - dependencies
    - endDate
    - projectKey
    - services
    - startDate
  - tool: delete-alert
    category: observability
    summary: Permanently delete an observability alert. THIS IS IRREVERSIBLE. Requires confirm=true to
      execute. Use get-alert first to verify you are deleting the right alert.
    annotations:
    - Destructive
    required_inputs:
    - alert_id
    - deleted
  - tool: toggle-alert
    category: observability
    summary: Enable or disable an observability alert without changing its configuration.
    annotations:
    - Idempotent
    required_inputs:
    - alert_id
    - enabled
  - tool: update-alert
    category: observability
    summary: Update an existing observability alert. Only the fields you provide are changed; everything
      else is preserved.
    annotations:
    - Destructive
    - Idempotent
    required_inputs:
    - alert_updated
  - tool: create-alert
    category: observability
    summary: Create a new observability alert that fires when a metric crosses a threshold.
    annotations: []
    required_inputs:
    - alert_created
    - alert_id
    - alert_url
  - tool: get-alert-firing-history
    category: observability
    summary: Show when an alert actually fired, and what state it is in now.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - current_state
    - firing_count
    - firings
    - last_fired_at
  - tool: get-alert
    category: observability
    summary: Get detailed information about a specific observability alert.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - alert_url
    - destinations
    - disabled
    - message_content
  - tool: list-alerts
    category: observability
    summary: List existing observability alerts for the project.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - alerts
    - total_count
  - tool: delete-dashboard
    category: observability
    summary: Permanently delete a dashboard (visualization) and all of its graphs. THIS IS IRREVERSIBLE.
      Requires confirm=true to execute. Use get-dashboard first to verify you are deleting the right dashboard.
    annotations:
    - Destructive
    required_inputs:
    - dashboard_id
    - deleted
  - tool: vent
    category: other
    summary: Report a missing capability, bug, parameter gap, or unclear error encountered while using
      LaunchDarkly MCP tools. This feedback is collected and triaged to improve the toolset. Use this
      when a tool is missing, returns an unexpected error, or lacks a needed parameter.
    annotations: []
    required_inputs: []
  - tool: get-doc
    category: account
    summary: Fetch the full markdown content of a LaunchDarkly documentation page.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: search-docs
    category: account
    summary: Search LaunchDarkly documentation to retrieve authoritative reference material for flags,
      targeting rules, experiments, segments, AgentControl configs, SDKs, API fields, rollouts, metrics,
      and more.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - query
  - tool: get-context-instances
    category: account
    summary: Get all stored instances of a specific context by kind and key. Returns every recorded occurrence
      of the context, including its full attribute set (e.g., merchantCountryCode, disbursementRail) and
      which SDK/application reported each instance.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: search-contexts
    category: account
    summary: Search for stored LaunchDarkly contexts in an environment by kind, key, or attribute value.
      Returns context records including their stored attributes (e.g., merchantCountryCode, disbursementRail)
      and when the context was last seen.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-service-connections-usage
    category: account
    summary: Get a time series of service connection minutes from your LaunchDarkly account. Use this
      for capacity planning, cost analysis, and before/after deploy comparisons (e.g. compare daily incremental
      minutes around a deploy date).
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: match-release-policies
    category: feature-management
    summary: Resolve which release policies would govern a flag in a given environment — a read-only dry-run
      of the server-side policy matching logic. Does not create or modify anything.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: create-automated-rollout-config
    category: feature-management
    summary: Record an automated rollout config in LaunchDarkly for a feature-flagged change.
    annotations: []
    required_inputs:
    - config_id
    - created
    - environments
    - flag_key
    - required_application_keys
    - warnings
  - tool: list-projects
    category: account
    summary: 'List LaunchDarkly projects in the account. Use to discover project keys before calling project-scoped
      tools. Filtering: use `query` to search by project name or key (case-insensitive), `tags` to filter
      by tag (all must match). Sorting: use `sort` with `name` or `-name`. Pagination: responses include
      `totalCount` and `pageInfo.offset`. To get the next page, set `offset` to the current offset + limit.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: query-change-history
    category: feature-management
    summary: Query the audit log to find what changed in a LaunchDarkly account. Returns a chronological
      list of changes (newest first) with who made each change and what they did.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - endDate
    - env
    - limit
    - projectKey
    - query
    - resourceKey
    - resourceKind
    - startDate
    - tags
  - tool: update-segment-targets
    category: feature-management
    summary: 'Add or remove individual context keys from a segment''s included or excluded lists. Included
      targets always match the segment. Excluded targets never match, even if rules would include them.
      Supported kinds: addIncludedTargets, removeIncludedTargets, addExcludedTargets, removeExcludedTargets.
      Each instruction requires contextKind and values. If the environment requires approval, the response
      includes requiresApproval: true and the attempted instructions; call `create-approval-request` with
      the returned instructions to submit it for review.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-segment-rules
    category: feature-management
    summary: 'Add, remove, or modify attribute-based targeting rules on a segment. Rules evaluate context
      attributes to determine segment membership. Clauses within a rule are ANDed; multiple rules use
      OR logic. Supported kinds: addRule, removeRule, addClauses, removeClauses, updateClause, addValuesToClause,
      removeValuesFromClause, reorderRules, updateRuleDescription, updateRuleRolloutAndContextKind. If
      the environment requires approval, the response includes requiresApproval: true and the attempted
      instructions; call `create-approval-request` with the returned instructions to submit it for review.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: get-segment
    category: feature-management
    summary: Get detailed configuration for a single segment in an environment. Returns rules, included
      targets, excluded targets, tags, and creation date. Use to verify segment state after creation or
      updates.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: create-segment
    category: feature-management
    summary: 'Create a new segment in a project environment. The segment is empty after creation — use
      update-segment-rules to add targeting rules or update-segment-targets to add individual context
      keys. Segment keys are immutable after creation: choose carefully. Pass viewKeys to link the new
      segment to one or more views at creation time (Views are an Enterprise feature).'
    annotations: []
    required_inputs: []
  - tool: list-segments
    category: feature-management
    summary: List segments in a project environment. Returns a paginated list with rule counts and target
      counts. Use query to search by name or key, tags to filter by tag, or view to only include segments
      linked to a view (Views are an Enterprise feature). Always list first to avoid creating duplicates.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: delete-prompt-snippet
    category: agentcontrol
    summary: Permanently delete a prompt snippet. THIS IS IRREVERSIBLE. Any AgentControl Config variations
      referencing this snippet will lose their reference. Requires confirm=true to execute.
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-prompt-snippet
    category: agentcontrol
    summary: Update an existing prompt snippet. Creates a new version of the snippet. All fields are optional
      — only provided fields are updated.
    annotations:
    - Idempotent
    required_inputs: []
  - tool: create-prompt-snippet
    category: agentcontrol
    summary: Create a new prompt snippet. A snippet is a reusable text block that can be referenced in
      AgentControl Config variation prompts using {{snippet-key}} syntax. Provide a unique key, display
      name, and the text content.
    annotations: []
    required_inputs: []
  - tool: get-prompt-snippet
    category: agentcontrol
    summary: Get a specific prompt snippet by key. Returns the snippet's name, text content, tags, version,
      and creation time.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-prompt-snippets
    category: agentcontrol
    summary: List prompt snippets in a project. Prompt snippets are reusable text blocks that can be referenced
      inside AgentControl Config variation prompts to keep common instructions consistent. Returns key,
      name, text, version, and tags.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: update-playground
    category: agentcontrol
    summary: Update an LLM playground's name, variants, or archived status. All fields are optional.
    annotations:
    - Idempotent
    required_inputs: []
  - tool: create-playground
    category: agentcontrol
    summary: Create a new LLM playground. A playground lets you compare AgentControl Config variations
      side-by-side. Provide a name and variants — each variant references an evaluation definition (by
      evaluationId) and a display position.
    annotations: []
    required_inputs: []
  - tool: get-playground
    category: agentcontrol
    summary: Get details about a specific LLM playground, including its variants (evaluation definitions
      and their positions).
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-playgrounds
    category: agentcontrol
    summary: List LLM playgrounds in a project. Returns playground names, variant counts, and timestamps.
      Supports search by name and pagination.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-evaluation-run-summary
    category: agentcontrol
    summary: Get the summary results of a completed evaluation run, including pass/fail counts and aggregate
      scores.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: run-evaluation
    category: agentcontrol
    summary: Start a new run of an AI evaluation. This executes the evaluation against the configured
      dataset and judge criteria. Returns the run ID and status.
    annotations: []
    required_inputs: []
  - tool: create-evaluation
    category: agentcontrol
    summary: Create a new AI evaluation definition. An evaluation defines a comparison between AgentControl
      Config variations using a dataset and judge criteria. After creation, use run-evaluation to start
      an evaluation run.
    annotations: []
    required_inputs: []
  - tool: get-evaluation
    category: agentcontrol
    summary: Get details about a specific evaluation definition, including its configuration and last
      run status.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-evaluations
    category: agentcontrol
    summary: List AgentControl Config evaluations in a project. Returns evaluation definitions with their
      names, associated config keys, and last run info.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: delete-dataset
    category: agentcontrol
    summary: Permanently delete an offline dataset and its associated metadata. THIS IS IRREVERSIBLE.
      Requires confirm=true to execute.
    annotations:
    - Destructive
    required_inputs: []
  - tool: create-dataset
    category: agentcontrol
    summary: Create a new offline dataset for AI evaluation. Provide a dataset name, filename, and format
      (csv, json, or jsonl). The dataset is created in pending status and must be uploaded separately.
      Returns the dataset ID and upload URL.
    annotations: []
    required_inputs: []
  - tool: get-dataset
    category: agentcontrol
    summary: Get details about a specific offline dataset by ID, including its processing status and row
      count.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-datasets
    category: agentcontrol
    summary: List offline datasets for a project. Returns id, name, status, row count, and creation info
      for each dataset. Datasets can be in pending, processing, completed, or failed status.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: stop-guarded-rollout
    category: feature-management
    summary: 'Stop an active guarded rollout on a flag''s default rule (fallthrough). This immediately
      halts the progressive rollout and locks the flag to its current state. If the environment requires
      approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request`
      with the returned instructions to submit it for review.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: start-guarded-rollout
    category: feature-management
    summary: 'Start a guarded rollout on a flag''s default rule (fallthrough). A guarded rollout progressively
      increases traffic to the test variation through a series of stages while monitoring metrics for
      regressions. Each stage specifies a rolloutWeight (percentage in thousandths, e.g. 10000 = 10%)
      and a monitoring window in milliseconds. Metrics define what to monitor and whether to notify or
      rollback on regression. Requires the flag to be on and not already have an active guarded rollout.
      If the environment requires approval, the response includes requiresApproval: true and the attempted
      instructions; call `create-approval-request` with the returned instructions to submit it for review.'
    annotations: []
    required_inputs: []
  - tool: get-experiment-metric-results
    category: experimentation
    summary: 'Get detailed statistical results for a single metric on an experiment iteration. Returns,
      per treatment: sample sizes (analyzedUnitCount, trafficCount, conversionCount), the observed mean
      and standard deviation, and a `statistics` block with the lift versus control (relativeDifferences:
      estimate plus lower/upper interval bounds and, for frequentist experiments, a per-comparison pValue),
      the overall pValue, Bayesian probabilities (probabilityToBeBest, probabilityToBeatBaseline, expectedLoss),
      and an isSignificant flag. Reads from LaunchDarkly''s internal analysis API. Defaults to the current
      iteration and the latest analysis; pass iterationId to target a previous iteration. Use disableMultipleComparisonCorrection
      / disableSequentialTesting to see uncorrected numbers. Use get-experiment-results for a cross-metric
      overview, or get-experiment to discover metric keys.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-experiment-results
    category: experimentation
    summary: 'Get an overall results summary for an experiment, across every metric on the current iteration.
      Discovers the iteration''s metrics, then fetches each metric''s analysis from LaunchDarkly''s internal
      results API and returns a compact per-metric summary: which treatment is leading (isBest) — the
      arm with the highest probability to beat the baseline for Bayesian experiments, or the lowest p-value
      versus control for frequentist (note: not significance-gated, so a treatment can be flagged leading
      even when nothing is significant) — each treatment''s lift versus control, whether it''s statistically
      significant, and sample sizes. Pass iterationId to summarize a previous iteration. For the full
      per-treatment statistics (intervals, p-values, Bayesian probabilities) on one metric, use get-experiment-metric-results.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: stop-experiment-iteration
    category: experimentation
    summary: 'Stop the currently running iteration of an experiment. Data collection ends and the iteration
      moves to the `stopped` status. A winning treatment is required to stop: pass `winningTreatmentId`
      (the `_id` of one of the iteration''s treatments, available from get-experiment) and an optional
      `winningReason` explaining the call. If the experiment was inconclusive, declare the baseline/control
      treatment as the winner.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: save-and-start-experiment-iteration
    category: experimentation
    summary: Stop the current running iteration, create a new draft iteration with the provided field
      updates applied, and start it — the API-recommended way to mutate treatments, metrics, methodology,
      or other fields that are locked while an iteration is running. Provide `changeJustification` to
      record why a new iteration is needed. Field inputs are the same as `update-experiment`; updates
      are checked against the new iteration's not_started mutability rules. Fields not allowed in not_started
      are returned under `skipped` rather than being sent.
    annotations:
    - Destructive
    required_inputs: []
  - tool: start-experiment-iteration
    category: experimentation
    summary: Start an experiment iteration. This begins data collection for the experiment's current draft
      iteration and starts allocating live end-user traffic across its treatments. The experiment's flag
      must be toggled on, a randomization unit must be set, and at least one treatment must have a non-zero
      allocation percent.
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-experiment
    category: experimentation
    summary: Update fields on an experiment or its current iteration. Which fields are mutable depends
      on the current iteration's status (not_started, running, stopped). This tool first reads the experiment's
      mutableFieldsByStatus, applies only the updates that are allowed for the current status via the
      updateExperimentFields semantic patch, and returns any rejected fields under `skipped` with the
      reason. If no provided field is mutable, the response includes `currentStatus` and `allowedFields`
      so you can retry with valid inputs.
    annotations:
    - Destructive
    required_inputs:
    - flagSettings
    - flags
    - metrics
    - treatments
  - tool: create-experiment
    category: experimentation
    summary: Create a new experiment on a flag or AgentControl Config. An experiment measures the impact
      of different variations on specified metrics. You must provide the initial iteration definition
      including a hypothesis, metrics, treatments, and flag configuration. One treatment must be marked
      as the baseline. Use `methodology` to pick the results-analysis approach (`bayesian` default, `frequentist`,
      or `export_only` for data-export-only mode). Use `analysisConfig` to set thresholds and multiple-comparison
      correction. Use `iteration.attributes` to declare slicing dimensions and `iteration.covariateId`
      to enable stratified sampling.
    annotations: []
    required_inputs: []
  - tool: get-experiment
    category: experimentation
    summary: Get detailed information about a specific experiment, including its treatments, metrics,
      and current iteration status.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-experiments
    category: experimentation
    summary: List experiments in a project, optionally filtered by environment. Returns key, name, description,
      and current iteration status for each experiment.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: delete-ai-tool
    category: agentcontrol
    summary: Permanently delete an AI tool definition. THIS IS IRREVERSIBLE. Any AgentControl Config variations
      referencing this tool will lose the attachment. Requires confirm=true to execute.
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-ai-tool
    category: agentcontrol
    summary: 'Update an AI tool definition''s description or schema. All fields are optional: only provided
      fields are updated. The schema should be a raw JSON Schema object with type, properties, and required
      fields.'
    annotations:
    - Idempotent
    required_inputs: []
  - tool: toggle-agentcontrol-config
    category: agentcontrol
    summary: 'Turn an AgentControl Config''s targeting on or off in a specific environment. Returns the
      previous and new state. This is equivalent to ''turnFlagOn'' / ''turnFlagOff'' for feature flags.
      If the environment requires approval, the response includes requiresApproval: true and the attempted
      instructions; call `create-agentcontrol-config-approval` with the returned instructions to submit
      it for review.'
    annotations:
    - Idempotent
    required_inputs: []
  - tool: get-keys
    category: account
    summary: Discover available data keys/dimensions for a product type.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - key_count
    - keys
    - product_type
  - tool: preview-graph
    category: agentcontrol
    summary: Preview a chart/graph inline WITHOUT saving it to a dashboard.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - _hint
    - bucketCount
    - display
    - endDate
    - expressions
    - groupBy
    - metrics
    - productType
    - projectKey
    - query
    - startDate
    - title
    - type
  - tool: create-graph
    category: agentcontrol
    summary: Add a chart/graph to an existing dashboard.
    annotations: []
    required_inputs:
    - Count
    - CountDistinct
    - Sum
  - tool: create-dashboard
    category: observability
    summary: Create a new empty dashboard (visualization) for organizing charts.
    annotations: []
    required_inputs:
    - dashboard_created
    - dashboard_id
    - dashboard_url
    - name
  - tool: get-dashboard
    category: observability
    summary: Get detailed information about a specific dashboard including all its graphs.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - dashboard_url
    - graph_count
    - graphs
    - id
    - name
    - time_preset
  - tool: list-dashboards
    category: observability
    summary: List existing dashboards (visualizations) for the project.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - dashboards
    - total_count
  - tool: query-flag-evaluations
    category: agentcontrol
    summary: Query flag evaluations for a session.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - direction
    - endDate
    - limit
    - projectKey
    - query
    - sessionSecureId
    - startDate
  - tool: query-timeline-events
    category: observability
    summary: Query timeline indicator events for a session.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - sessionSecureId
  - tool: query-sessions
    category: observability
    summary: Query project sessions.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - count
    - endDate
    - page
    - projectKey
    - query
    - sortDesc
    - sortField
    - startDate
  - tool: query-error-groups
    category: observability
    summary: Query project error groups.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - count
    - endDate
    - page
    - projectKey
    - query
    - startDate
  - tool: query-aggregations
    category: observability
    summary: Retrieve bucketed, aggregated values over time for a product type.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - Count
    - CountDistinct
    - aggregator
    - column
    - endDate
    - expressions
    - groupBy
    - productType
    - projectKey
    - query
    - startDate
  - tool: query-traces
    category: observability
    summary: Query project traces.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - direction
    - endDate
    - limit
    - projectKey
    - query
    - sortColumn
    - sortDirection
    - startDate
  - tool: query-logs
    category: observability
    summary: Query project logs.
    annotations:
    - Read-only
    - Idempotent
    required_inputs:
    - direction
    - endDate
    - limit
    - projectKey
    - query
    - startDate
  - tool: get-sdk-active
    category: account
    summary: Check whether any SDKs have been active in a given environment. Returns true if any SDK has
      initialized or sent events in the environment. Use this to verify that an environment is actually
      in use before cleanup. Optionally filter by sdkName or sdkWrapperName to check a specific SDK.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-environment
    category: account
    summary: 'Get a LaunchDarkly environment and its SDK keys: server-side SDK key, client-side ID, and
      mobile key. Use this to retrieve the client-side ID needed to initialize a browser or mobile SDK.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-project
    category: account
    summary: Get a LaunchDarkly project with its environments and SDK keys. Use to retrieve SDK keys for
      an existing project or verify a project exists.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: create-project
    category: account
    summary: Create a new LaunchDarkly project. Returns the project with its environments and SDK keys.
      Project keys must be lowercase with hyphens, starting with a letter. Production and Test environments
      are created by default.
    annotations: []
    required_inputs: []
  - tool: list-release-policies
    category: feature-management
    summary: List release policies for a project. Each policy defines preferred release methods and the
      metrics or metric groups that automatically attach to guarded rollouts when the policy's conditions
      match (e.g. specific environments or flag tags).
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-metric-events
    category: experimentation
    summary: List recent event keys received by a LaunchDarkly project — used to check which events are
      actively flowing before creating a metric. Returns up to 50 event keys with last-seen timestamps.
      If the event key you need isn't here, it may not be instrumented yet.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: create-metric
    category: experimentation
    summary: Create a new metric in a LaunchDarkly project.
    annotations: []
    required_inputs: []
  - tool: get-metric
    category: experimentation
    summary: 'Get full details for a single LaunchDarkly metric: measureType, eventKey, successCriteria,
      unit, description, tags, creation date, and attached flag count. Use after create-metric to verify
      the result, or to inspect an existing metric before modifying it.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-metrics
    category: experimentation
    summary: List metrics in a LaunchDarkly project. Returns key, name, measureType (count/occurrence/value),
      eventKey, successCriteria, tags, and how many flags each metric is attached to.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: delete-agent-graph
    category: agentcontrol
    summary: Permanently delete an agent graph and all of its edges. THIS IS IRREVERSIBLE. Requires confirm=true
      to execute.
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-agent-graph
    category: agentcontrol
    summary: Update an agent graph's metadata or structure. All fields are optional. If rootConfigKey
      or edges are provided, both must be present and will fully replace the existing graph structure.
      Pass name or description to update metadata only.
    annotations:
    - Destructive
    required_inputs: []
  - tool: create-agent-graph
    category: agentcontrol
    summary: Create a new agent graph in a project. An agent graph defines a directed graph of AgentControl
      Configs for multi-agent workflows. Provide a rootConfigKey and edges to define the graph structure,
      or create the graph with just metadata and add edges later via update-agent-graph. If rootConfigKey
      or edges are provided, both must be present.
    annotations: []
    required_inputs: []
  - tool: get-agent-graph
    category: agentcontrol
    summary: Get a specific agent graph by key, including its full edge structure. Each edge connects
      a source AgentControl Config to a target AgentControl Config with optional handoff data.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-agent-graphs
    category: agentcontrol
    summary: List all agent graphs in a project. Returns metadata for each graph including key, name,
      description, and root config key. Does not include edge data — use get-agent-graph to retrieve full
      graph structure.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: invite-members
    category: account
    summary: Invite one or more people to the LaunchDarkly account by email. Each invitee receives an
      email invitation to join. Optionally assign a role (reader, writer, admin) — defaults to reader
      if not specified.
    annotations:
    - Open-world
    required_inputs: []
  - tool: find-members
    category: account
    summary: 'Search for LaunchDarkly account members and return their IDs. Supports flexible matching:'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-member-self
    category: account
    summary: Return the member ID, profile, and team memberships for the currently authenticated user.
      Use this whenever the user refers to themselves ('my metrics', 'created by me', 'assigned to me')
      to resolve their member ID before calling tools that require a maintainerId or similar identifier,
      or to resolve one of their team keys before calling tools that require a maintainerTeamKey. If the
      member belongs to more than one team, ask which one to use rather than guessing. If the server returns
      `token_expired`, re-authenticate the Launchdarkly MCP server connection in your MCP client and retry.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: create-ai-tool
    category: agentcontrol
    summary: 'Create a new AI tool definition in a project. The schema should be a raw JSON Schema object
      with type, properties, and required fields (e.g. {"type": "object", "properties": {...}}). Do NOT
      use the OpenAI function calling wrapper format. After creation, attach the tool to a variation using
      update-agentcontrol-config-variation.'
    annotations: []
    required_inputs: []
  - tool: get-ai-tool
    category: agentcontrol
    summary: Get a single AI tool definition including its full schema. Use to inspect a tool's parameters
      before attaching it to an AgentControl Config variation.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-ai-tools
    category: agentcontrol
    summary: List AI tool definitions in a project. Returns each tool's key, description, and schema.
      Tools are attached to AgentControl Config variations to give models function-calling capabilities.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: update-agentcontrol-config-rollout
    category: agentcontrol
    summary: 'Update the default (fallthrough) rule for an AgentControl Config in an environment. Set
      a percentage rollout across variations, or serve a single variation to all unmatched contexts. Weights
      must sum to 100. Use human-friendly percentages (e.g., 80 for 80%). Accepts a variation key (from
      get-agentcontrol-config) or variation name (from get-agentcontrol-config-targeting); the tool resolves
      either to the internal variation _id (UUID) before patching. If the environment requires approval,
      the response includes requiresApproval: true and the attempted instructions; call `create-agentcontrol-config-approval`
      with the returned instructions to submit it for review.'
    annotations:
    - Idempotent
    required_inputs: []
  - tool: get-agentcontrol-config-targeting
    category: agentcontrol
    summary: Read the targeting configuration for an AgentControl Config in a specific environment. Returns
      variations (with their _id UUIDs and names), individual targets, custom rules, fallthrough (default
      rule), and off variation. The variation name returned here can be passed as 'variationKey' to update-agentcontrol-config-targeting,
      update-agentcontrol-config-rollout, and update-agentcontrol-config-targets. Alternatively, use get-agentcontrol-config
      to obtain the variation's slug key.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: clone-agentcontrol-config-variation
    category: agentcontrol
    summary: 'Clone an existing AgentControl Config variation with selective overrides. Reads the source
      variation, applies any provided overrides (model, instructions, messages, parameters, tools), and
      creates a new variation. Returns both the source and created variation so you can compare the diff.
      Use this for A/B experimentation: change one thing at a time while keeping everything else constant.'
    annotations: []
    required_inputs: []
  - tool: delete-agentcontrol-config-variation
    category: agentcontrol
    summary: Permanently delete an AgentControl Config variation. THIS IS IRREVERSIBLE. Requires confirm=true
      to execute.
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-agentcontrol-config-variation
    category: agentcontrol
    summary: 'Update an AgentControl Config variation''s name, description, model, instructions/messages,
      parameters, attached tools, or judge configuration. All fields are optional: only provided fields
      are updated. Pass ''name'' to rename the variation in place without recreating it (avoids changing
      the variation _id). To attach tools, pass the ''tools'' array with {key, version} entries (create
      tools first with create-ai-tool). Pass an empty tools array to detach all tools. To attach judges,
      pass judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries. Pass an empty
      judges array to detach all judges.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: create-agentcontrol-config-variation
    category: agentcontrol
    summary: Create a variation for an AgentControl Config. A variation defines the model, prompts, parameters,
      and tools. modelConfigKey must be in Provider.model-id format (e.g. OpenAI.gpt-4o, Anthropic.claude-sonnet-4-5)
      for models to display correctly in the UI. Agent-mode configs use 'instructions' (a string); completion-mode
      configs use 'messages' (an array of {role, content} objects). To attach AI tools, pass the 'tools'
      array with {key, version} entries (create tools first with create-ai-tool). To attach judges, pass
      judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries.
    annotations: []
    required_inputs: []
  - tool: get-agentcontrol-config-health
    category: agentcontrol
    summary: 'Health check for an AgentControl Config. Detects common issues: missing models (NO MODEL
      in UI), missing prompts, orphaned tool references, and empty configs with no variations. Returns
      a health verdict (healthy, warning, unhealthy) with specific issues and per-variation summaries.
      Run before updating or experimenting with a config.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: setup-agentcontrol-config
    category: agentcontrol
    summary: 'Create an AgentControl Config with its first variation in one step. This is the recommended
      way to set up a new AgentControl Config: it creates the config, adds a variation with model and
      prompts, and verifies everything is configured correctly. Returns the full config detail with variation.
      To attach AI tools, pass the ''tools'' array with {key, version} entries. IMPORTANT: evaluationMetricKey
      (format: $ld:ai:judge:<suffix>) is REQUIRED when mode is ''judge''. Pass viewKeys to link the new
      config to one or more views at creation time (Views are an Enterprise feature). Use create-agentcontrol-config
      + create-agentcontrol-config-variation separately only when you need more control.'
    annotations: []
    required_inputs: []
  - tool: delete-agentcontrol-config
    category: agentcontrol
    summary: 'Permanently delete an AgentControl Config. THIS IS IRREVERSIBLE. Requires confirm=true to
      execute. Prefer archiving (update-agentcontrol-config with archived: true) when possible.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-agentcontrol-config
    category: agentcontrol
    summary: 'Update an AgentControl Config''s metadata: name, description, tags, or archive status. Does
      NOT modify variations: use update-agentcontrol-config-variation for model, prompt, or parameter
      changes. Set archived: true to archive (reversible).'
    annotations:
    - Idempotent
    required_inputs: []
  - tool: create-agentcontrol-config
    category: agentcontrol
    summary: 'Create a new AgentControl Config in a project. This creates the config shell: use create-agentcontrol-config-variation
      next to add a model, prompts, and parameters. Mode determines whether variations use ''instructions''
      (agent), ''messages'' (completion), or ''messages'' (judge). Judge-mode configs evaluate other AgentControl
      Config outputs. IMPORTANT: evaluationMetricKey (format: $ld:ai:judge:<suffix>) is REQUIRED when
      mode is ''judge''; omitting it will cause a 400 error. For agent and completion mode it is not accepted.
      Pass viewKeys to link the new config to one or more views at creation time (Views are an Enterprise
      feature).'
    annotations: []
    required_inputs: []
  - tool: get-agentcontrol-config
    category: agentcontrol
    summary: Get detailed configuration for a single AgentControl Config including all its variations.
      Each variation includes its model, instructions or messages, parameters, attached tools, and judgeConfiguration
      (attached judges with judgeConfigKey and samplingRate). For judge-mode configs the response also
      includes evaluationMetricKey.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-agentcontrol-configs
    category: agentcontrol
    summary: Search and browse AgentControl Configs in a project. Returns a paginated list with key, name,
      mode (agent, completion, or judge), tags, variation count, and a `usedInGraphs` array listing the
      agent graph keys that reference each config (as the graph root or as an edge source/target). An
      empty `usedInGraphs` means the config is not referenced by any graph (orphaned). If graph usage
      cannot be loaded, `usedInGraphs` is omitted entirely (rather than empty) so an absent field is never
      mistaken for orphaned. Use query to search by name or key, tags to filter by tag, or view to only
      include configs linked to a view (Views are an Enterprise feature).
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: apply-approval-request
    category: feature-management
    summary: 'Apply an already-approved flag approval request. This executes the changes that were approved
      by reviewers. Only works on requests with reviewStatus ''approved''. Does NOT approve requests:
      that must be done by a human reviewer. Use list-approval-requests to get the request id.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: list-approval-requests
    category: feature-management
    summary: List pending approval requests for a flag in an environment. Shows status, review state,
      and who requested the change. Use to check on approval progress after creating a request.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: create-approval-request
    category: feature-management
    summary: 'Create an approval request for a flag change in an environment that requires approvals.
      Requires at least one reviewer: notifyMemberIds and/or notifyTeamKeys. If the user named a person,
      resolve them with find-members and pass the returned id. If they did not name anyone, ask who should
      review before calling this tool. Provide the same semantic patch instructions you would use for
      a direct change. The request will be reviewed by approvers before taking effect. Does NOT approve
      the request: that must be done by a human reviewer.'
    annotations: []
    required_inputs: []
  - tool: check-removal-readiness
    category: other
    summary: 'Detailed safety check before removing a feature flag. Checks dependencies, code references,
      active targeting, expiring targets, and cross-environment status. Returns a readiness verdict: ''safe''
      (proceed), ''caution'' (review warnings), or ''blocked'' (must resolve blockers first). Always run
      this before archive-flag or delete-flag.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: manage-expiring-targets
    category: feature-management
    summary: List, add, update, or remove expiring targets on a flag. Expiring targets are automatically
      removed from targeting after a specified date. Dates are shown as ISO strings with days-until-expiry
      computed. Variation IDs are resolved to human-readable names.
    annotations:
    - Destructive
    required_inputs: []
  - tool: delete-flag
    category: feature-management
    summary: Permanently delete a feature flag. THIS IS IRREVERSIBLE. Requires confirm=true to execute.
      Always call check-removal-readiness first and only delete if it returns 'safe'. Prefer archive-flag
      (reversible) when possible.
    annotations:
    - Destructive
    required_inputs: []
  - tool: archive-flag
    category: feature-management
    summary: Archive a feature flag (reversible). This is a soft-delete that can be undone. Recommended
      as the first step before permanent deletion. Always run check-removal-readiness before archiving.
    annotations:
    - Destructive
    - Idempotent
    required_inputs: []
  - tool: copy-flag-config
    category: feature-management
    summary: 'Copy a flag''s targeting configuration from one environment to another. Common use: promote
      from staging to production. Optionally select which aspects to copy: targeting, rules, offVariation,
      prerequisites, on state. If the target environment requires approval, the response includes requiresApproval:
      true and an approvalUrl; follow the approvalUrl to submit the copy request for review.'
    annotations:
    - Destructive
    - Idempotent
    required_inputs: []
  - tool: update-prerequisites
    category: feature-management
    summary: 'Add or remove prerequisites for a flag in a specific environment. Prerequisites are other
      flags that must evaluate to specific variations before this flag is evaluated. Use addPrerequisite
      to migrate prerequisites onto a new flag, or removePrerequisite + addPrerequisite to update dependent
      flags to point to a new key. If the environment requires approval, the response includes requiresApproval:
      true and the attempted instructions; call `create-approval-request` with the returned instructions
      to submit it for review.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-individual-targets
    category: other
    summary: 'Add or remove specific users or contexts from individual flag targeting. Individual targets
      are the highest priority: they override all rules. Supported instruction kinds: addTargets, removeTargets,
      replaceTargets. To target non-user context kinds (e.g. organization), include contextKind on the
      instruction (e.g. { kind: ''addTargets'', contextKind: ''organization'', values: [''org-123''],
      variationId: ''<id>'' }). Note: addContextTargets and removeContextTargets are NOT supported by
      the LD API; use addTargets/removeTargets with contextKind instead. Responses truncate long lists.
      If the environment requires approval, the response includes requiresApproval: true and the attempted
      instructions; call `create-approval-request` with the returned instructions to submit it for review.'
    annotations:
    - Destructive
    required_inputs: []
  - tool: update-targeting-rules
    category: feature-management
    summary: Add, remove, or modify custom targeting rules for a flag in an environment. Rules evaluate
      top-to-bottom; first matching rule wins. Use get-flag to look up rule _ids, clause _ids, and variation
      _ids before constructing instructions.
    annotations:
    - Destructive
    required_inputs:
    - addClauses
    - addRule
    - removeClauses
    - removeRule
    - reorderRules
    - updateRuleVariationOrRollout
  - tool: update-rollout
    category: feature-management
    summary: 'Change the default rule (fallthrough) for a flag. Set a percentage rollout across variations
      or serve a single variation to all unmatched users. Weights must sum to 100. Use human-friendly
      percentages (e.g., 80 for 80%). If the environment requires approval, the response includes requiresApproval:
      true and the attempted instructions; call `create-approval-request` with the returned instructions
      to submit it for review.'
    annotations:
    - Idempotent
    required_inputs: []
  - tool: toggle-flag
    category: feature-management
    summary: 'Turn a feature flag''s targeting on or off in a specific environment. Returns the previous
      and new state. If the environment requires approval, the response includes requiresApproval: true
      and the attempted instructions; call `create-approval-request` with the returned instructions to
      submit it for review.'
    annotations:
    - Idempotent
    required_inputs: []
  - tool: update-flag-settings
    category: feature-management
    summary: 'Update a flag''s top-level settings: name, description, tags, temporary/permanent status,
      maintainer, default variations, or custom properties. Does NOT modify per-environment targeting,
      rollouts, or rules: use the targeting tools for those. Supported instruction kinds: updateName,
      updateDescription, addTags, removeTags, markTemporary, markPermanent, updateMaintainerMember, updateMaintainerTeam,
      addCustomProperties, replaceCustomProperties, removeCustomProperties, updateDefaultVariation. updateMaintainerTeam
      takes the same Value shape as updateMaintainerMember but with a team key instead of a member id
      (e.g. { kind: ''updateMaintainerTeam'', value: ''team-key'' }). Only include a maintainer instruction
      when the user explicitly asked to change the maintainer — don''t reassign it as a side effect of
      some other requested edit. addCustomProperties adds a new custom property: { kind, key, name, values[]
      }. replaceCustomProperties replaces an existing custom property''s values: { kind, key, name, values[]
      }. removeCustomProperties removes specific values from a custom property: { kind, key, values[]
      }. updateDefaultVariation sets the flag-level default variation indices used when new environments
      are provisioned: { kind, onVariation?: number, offVariation?: number } where onVariation/offVariation
      are zero-based variation indices.'
    annotations:
    - Idempotent
    required_inputs: []
  - tool: create-flag
    category: feature-management
    summary: 'Create a new feature flag in a project. Defaults to a boolean temporary flag. After creation
      the flag is OFF in all environments: use toggle-flag to enable it.'
    annotations: []
    required_inputs: []
  - tool: get-flag-status-across-envs
    category: feature-management
    summary: Check a flag's lifecycle status across all environments. Returns per-environment state (active,
      inactive, new, launched) and a summary of which environments the flag is active, inactive, or launched
      in. Use before cleanup to verify the flag is inactive everywhere.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: find-stale-flags
    category: feature-management
    summary: 'Find feature flags that are candidates for cleanup. Returns a prioritized list of stale
      flags sorted by staleness (worst first). Categories: inactive_30d (no requests in period), launched_no_changes
      (fully rolled out, no recent changes), never_requested (created but never evaluated). Defaults to
      showing temporary flags inactive for 30+ days.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-flag-health
    category: feature-management
    summary: 'Get combined health view for a single flag: lifecycle state, last-requested timestamp, targeting
      summary (rules count, targets count, on/off), age, and whether it''s temporary. Use this to assess
      if a flag is stale or needs attention.'
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: get-flag
    category: feature-management
    summary: Get detailed configuration for a single feature flag scoped to a specific environment. Returns
      the full targeting tree including rules, individual targets, fallthrough, prerequisites, and variation
      details.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
  - tool: list-flags
    category: feature-management
    summary: Search and browse feature flags in a project. Returns a paginated list scoped to a single
      environment.
    annotations:
    - Read-only
    - Idempotent
    required_inputs: []
crosswalk: mcp/launchdarkly-tool-crosswalk.yml