generated: '2026-08-02'
method: searched
status: published
source: https://docs.bigeye.com/docs/bigeye-mcp-server
server:
  name: bigeye
  transport: http
  url: https://mcpgateway.bigeye.com/mcp
  hosted: true
  maturity: public beta (released July 2026)
  protocol: Model Context Protocol
  open_source: true
  repository: https://github.com/bigeyedata/bigeye-mcp-server
  self_hostable: true
  self_host_options:
  - docker
  - python
authentication:
  style: api-key request headers (no OAuth)
  headers:
  - header: Authorization
    value: apikey <YOUR_API_KEY>
    required: true
    note: Literal "apikey" prefix — not "Bearer". Same Personal or Service Account API key used by the
      REST API.
  - header: x-bigeye-workspace-id
    value: <YOUR_WORKSPACE_ID>
    required: true
    note: Integer workspace ID from Settings > Workspaces.
  - header: x-bigeye-url
    value: https://app.bigeye.com
    required: false
    note: Only needed for customers on a non-default Bigeye stack.
  docs: https://docs.bigeye.com/docs/using-api-keys
introspection:
  method: tools/list
  anonymous: true
  http_status: 200
  transport: SSE (text/event-stream) JSON-RPC response
  tools_returned: 56
  file: bigeye-mcp-tools-list.json
  note: tools/list answered without credentials and returned every tool with a real inputSchema and outputSchema;
    the schemas below are harvested verbatim, not inferred.
clients_documented:
- Claude Code
- Snowflake Cortex Code (CoCo)
- GitHub Copilot CLI
tool_count: 56
tools:
- name: list_resources
  category: catalog
  description: List all available MCP resources for quick data access.
  input_arguments: []
  required: []
- name: get_health_status
  category: platform
  description: Check the health and connectivity of the Bigeye API. Returns API status and version.
  input_arguments: []
  required: []
- name: get_current_user
  category: platform
  description: Get the currently authenticated Bigeye user (the API key owner). Returns their integer
    'id', email, name, and accessible workspaces. Use this to answer 'who am I' and to resolve the current
    user's ID for assignee filtering — e.g. to find issues assigned to the current user, call this, then
    list_issues(assignee_ids=[id]).
  input_arguments: []
  required: []
- name: list_issues
  category: issues
  description: List data quality issues across the workspace. Supports filtering by status (ISSUE_STATUS_NEW,
    ISSUE_STATUS_ACKNOWLEDGED, ISSUE_STATUS_CLOSED, ISSUE_STATUS_MONITORING, ISSUE_STATUS_MERGED), schema,
    assignee, and collection. Returns compact summaries by default. Best for broad views like 'show all
    open issues'. To find issues assigned to the current user, first call get_current_user to get their
    integer 'id', then pass it as assignee_ids=[id]. To filter by collection, call list_collections first
    to resolve a collection name to its ID. For issues on a specific table, use list_table_issues instead.
  input_arguments:
  - assignee_ids
  - collection_ids
  - compact
  - max_issues
  - page_cursor
  - page_size
  - schema_names
  - statuses
  required: []
- name: get_issue
  category: issues
  description: Get full details for a single issue by its internal ID (not display name). Returns event
    history, metric details, and metadata. To find an issue's internal ID from its display name, use search_issues
    first.
  input_arguments:
  - issue_id
  required:
  - issue_id
- name: search_issues
  category: issues
  description: Find issues or incidents by their display name — the number shown in the Bigeye UI (e.g.
    '10921'). ALWAYS use this when a user references an issue by number. Returns matching issues with
    their internal IDs for use with get_issue, update_issue, and other tools.
  input_arguments:
  - exact_match
  - name_query
  - statuses
  required:
  - name_query
- name: search_schemas
  category: catalog
  description: Search the Bigeye data catalog for schemas by name. Returns matching schemas with their
    internal IDs and warehouse context.
  input_arguments:
  - limit
  - query
  required:
  - query
- name: search_tables
  category: catalog
  description: Search the Bigeye data catalog for tables by name. Returns matching tables with their internal
    IDs, schema, and warehouse context.
  input_arguments:
  - limit
  - query
  required:
  - query
- name: search_columns
  category: catalog
  description: Search the Bigeye data catalog for columns by name. Returns matching columns with their
    internal IDs, data type, and the table/schema/warehouse they belong to.
  input_arguments:
  - limit
  - query
  required:
  - query
- name: list_related_issues
  category: issues
  description: List issues related to a given issue via upstream/downstream lineage. Returns related issues
    with root cause flags (isRootCause=true). Requires internal issue ID.
  input_arguments:
  - starting_issue_id
  required:
  - starting_issue_id
- name: list_table_issues
  category: issues
  description: List data quality issues for a specific table by name. Best for investigating a known table.
    For workspace-wide issues use list_issues. Requires table_name.
  input_arguments:
  - schema_name
  - statuses
  - table_name
  - warehouse_name
  required:
  - table_name
- name: create_incident
  category: issues
  description: Create an incident by merging related issues, or add issues to an existing incident. Requires
    at least 2 issue IDs for new incidents, or 1 issue ID plus an existing_incident_id.
  input_arguments:
  - existing_incident_id
  - incident_name
  - issue_ids
  required:
  - issue_ids
- name: get_resolution_steps
  category: issues
  description: Get recommended resolution steps for an issue. Returns step-by-step guidance for remediation.
    Requires internal issue ID.
  input_arguments:
  - issue_id
  required:
  - issue_id
- name: update_issue
  category: issues
  description: 'Update an issue''s status, priority, or add a timeline message. Valid statuses: ISSUE_STATUS_NEW,
    ISSUE_STATUS_ACKNOWLEDGED, ISSUE_STATUS_CLOSED, ISSUE_STATUS_MONITORING, ISSUE_STATUS_MERGED. When
    closing, requires a closing_label (METRIC_RUN_LABEL_TRUE_NEGATIVE, METRIC_RUN_LABEL_FALSE_POSITIVE,
    etc.).'
  input_arguments:
  - closing_label
  - issue_id
  - message
  - new_status
  - priority
  required:
  - issue_id
- name: delete_incident_members
  category: issues
  description: Remove issues from an incident. Specify individual issue_ids to unmerge, or parent_issue_ids
    to unmerge all children from an incident.
  input_arguments:
  - assignee_id
  - issue_ids
  - new_status
  - parent_issue_ids
  required: []
- name: list_table_metrics
  category: monitoring
  description: List all metrics (monitors) configured on a table from the live Bigeye API. Returns full
    metric configurations including schedules, thresholds, lookback windows, and which data dimension
    each metric belongs to. For a quick coverage gap analysis, use get_table_dimension_coverage instead.
  input_arguments:
  - schema_name
  - table_name
  required:
  - table_name
- name: list_data_sources
  category: catalog
  description: List all data sources (warehouses) connected to Bigeye. Returns source names, types (SNOWFLAKE,
    DATABRICKS, etc.), and connection details. Prefer list_sources (knowledgebase) for faster cached results.
  input_arguments: []
  required: []
- name: list_collections
  category: catalog
  description: List all collections in the workspace. Collections are curated groups of metrics (data
    products, domains, etc.). Returns each collection's id, name, description, and metricIds. Use this
    to resolve a collection name to its ID, then pass it to list_issues(collection_ids=[...]) to see that
    collection's issues.
  input_arguments: []
  required: []
- name: get_dataset_health_summary
  category: platform
  description: 'Get a health overview of datasets (tables): monitoring status and open issues per dataset,
    rolled up per schema. This is the recommended single-call tool for questions like "show me the health
    of my datasets" or "which tables are alerting?".'
  input_arguments:
  - max_tables
  - schema_name
  - warehouse_name
  required: []
- name: get_lineage_graph
  category: lineage
  description: Get the full lineage graph (upstream/downstream/both) from a starting node. Returns nodes
    and edges showing data flow. Requires node_id from search_lineage_nodes.
  input_arguments:
  - direction
  - include_issues
  - max_depth
  - node_id
  required:
  - node_id
- name: get_lineage_node
  category: lineage
  description: Get details for a specific lineage node (type, name, properties). Requires node_id.
  input_arguments:
  - node_id
  required:
  - node_id
- name: list_lineage_node_issues
  category: lineage
  description: List issues for a lineage node by its node_id. Best for when you already have a node_id
    from search_lineage_nodes. If you only have a table name, use list_table_issues instead.
  input_arguments:
  - node_id
  required:
  - node_id
- name: get_upstream_root_causes
  category: platform
  description: Analyze upstream lineage to identify root causes of data quality issues. Traverses upstream
    from a node to find the origin of problems. Requires node_id.
  input_arguments:
  - max_depth
  - node_id
  required:
  - node_id
- name: get_downstream_impact
  category: platform
  description: Analyze downstream impact of issues at a lineage node, categorized by type (analytics,
    data products, critical). Returns severity assessment and stakeholder notifications. Requires node_id.
  input_arguments:
  - impact_focus
  - include_integration_entities
  - max_depth
  - node_id
  required:
  - node_id
- name: get_issue_lineage_trace
  category: lineage
  description: 'Trace a data quality issue end-to-end through lineage: upstream root causes to downstream
    impact. Requires internal issue_id (from search_issues, not the display name).'
  input_arguments:
  - include_impact_analysis
  - include_root_cause_analysis
  - issue_id
  - max_depth
  required:
  - issue_id
- name: lineage_track_data_access
  category: lineage
  description: Track data assets accessed by an AI agent.
  input_arguments:
  - agent_name
  - qualified_names
  required:
  - qualified_names
- name: lineage_get_tracking_status
  category: lineage
  description: Get the current status of lineage tracking.
  input_arguments: []
  required: []
- name: lineage_commit_agent
  category: lineage
  description: Commit tracked data access to Bigeye's lineage graph.
  input_arguments:
  - clear_after_commit
  - rebuild_graph
  required: []
- name: lineage_clear_tracked_assets
  category: lineage
  description: Clear all tracked data assets without committing.
  input_arguments: []
  required: []
- name: lineage_cleanup_agent_edges
  category: lineage
  description: Clean up old lineage edges for the AI agent.
  input_arguments:
  - retention_days
  required: []
- name: search_lineage_nodes
  category: lineage
  description: 'Find lineage node IDs by path pattern (e.g. ''WAREHOUSE/SCHEMA/TABLE''). Supports wildcards
    (''*/*/ORDERS''). Best for: getting a node_id required by get_lineage_graph, get_downstream_impact,
    and other lineage tools.'
  input_arguments:
  - limit
  - node_type
  - search_string
  - workspace_id
  required: []
- name: lineage_explore_catalog
  category: lineage
  description: Explore tables in Bigeye's catalog. For browsing the data catalog, prefer list_tables +
    list_schemas (knowledgebase).
  input_arguments:
  - page_size
  - schema_name
  - search_term
  - warehouse_name
  required: []
- name: lineage_delete_node
  category: lineage
  description: Delete a custom lineage node from Bigeye's lineage graph.
  input_arguments:
  - force
  - node_id
  required:
  - node_id
- name: list_report_upstream_issues
  category: issues
  description: List upstream data quality issues affecting a BI report or dashboard. Requires the report's
    lineage node_id. To discover reports/dashboards first, use list_catalog_entities (knowledgebase).
  input_arguments:
  - report_id
  required:
  - report_id
- name: get_table_profile
  category: profiling
  description: Get the data profile report for a table including column statistics, data distribution,
    and profile history. Requires table_id.
  input_arguments:
  - table_id
  required:
  - table_id
- name: create_profile_job
  category: profiling
  description: Queue a new data profiling job for a table. Returns a workflow ID to track progress with
    get_profile_job_status. Requires table_id.
  input_arguments:
  - table_id
  required:
  - table_id
- name: get_profile_job_status
  category: profiling
  description: Check the status of a profiling job (queued, running, completed). Requires table_id.
  input_arguments:
  - table_id
  required:
  - table_id
- name: list_dimensions
  category: monitoring
  description: List all data-quality dimensions with their metric type mappings. Returns each dimension's
    name, top-level category (PIPELINE_RELIABILITY or DATA_QUALITY), and the metric types that belong
    to it. For a table-specific coverage analysis that maps dimensions to existing monitors, use get_table_dimension_coverage.
  input_arguments: []
  required: []
- name: get_dimension
  category: monitoring
  description: Get full details for a single Data Dimension by its ID. Returns the dimension's name, description,
    and entity metadata.
  input_arguments:
  - dimension_id
  required:
  - dimension_id
- name: create_dimension
  category: monitoring
  description: Create a new Data Dimension in the Bigeye workspace.
  input_arguments:
  - description
  - name
  required:
  - name
- name: update_dimension
  category: monitoring
  description: Update an existing Data Dimension's name or description.
  input_arguments:
  - description
  - dimension_id
  - name
  required:
  - dimension_id
- name: delete_dimension
  category: monitoring
  description: Delete a Data Dimension by its ID. This action is permanent.
  input_arguments:
  - dimension_id
  required:
  - dimension_id
- name: list_table_level_metrics
  category: monitoring
  description: List metric types that are table-level (not column-level). Returns metric names like FRESHNESS,
    VOLUME, COUNT_ROWS, etc. Use this to distinguish table-level from column-level metrics when analyzing
    coverage.
  input_arguments: []
  required: []
- name: create_metric
  category: monitoring
  description: Create a new metric (monitor) on a table. Supports predefined metric types like COUNT_ROWS,
    PERCENT_NULL, FRESHNESS, etc.
  input_arguments:
  - column_name
  - description
  - filters
  - group_bys
  - lookback_interval_type
  - lookback_interval_value
  - lookback_type
  - metric_type
  - name
  - schema_name
  - table_id
  - table_name
  required:
  - metric_type
  - table_name
- name: get_table_dimension_coverage
  category: monitoring
  description: 'Analyze which data quality dimensions are covered by monitors on a table and which have
    gaps. Automatically joins the workspace''s dimension taxonomy, the table''s column metadata, and existing
    metrics to produce: per-column coverage, table-level coverage, an aggregate score, and a prioritized
    gap list with suggested metric types. This is the recommended single-call tool for answering ''what
    monitoring is missing on this table?'''
  input_arguments:
  - schema_name
  - table_id
  - table_name
  required: []
- name: get_column_dimension_coverage
  category: monitoring
  description: Analyze dimension coverage for specific columns in a table. Same analysis as get_table_dimension_coverage
    but filtered to the requested columns. Use this when you already know which columns to investigate
    — for example, after identifying columns with issues or when a user asks about specific fields. Always
    includes table-level dimension coverage for context.
  input_arguments:
  - column_names
  - schema_name
  - table_id
  - table_name
  required: []
- name: list_tags
  category: tags
  description: List or search workspace tags. Returns tag IDs, names, and colors. Use search to filter
    by name.
  input_arguments:
  - page_cursor
  - page_size
  - search
  required: []
- name: create_tag
  category: tags
  description: Create a new workspace tag. Tags can be applied to metrics, tables, columns, and other
    entities.
  input_arguments:
  - color_hex
  - name
  required:
  - name
- name: update_tag
  category: tags
  description: Update an existing workspace tag's name or color.
  input_arguments:
  - color_hex
  - name
  - tag_id
  required:
  - tag_id
- name: delete_tag
  category: tags
  description: Delete a workspace tag. This removes the tag from all entities it was applied to.
  input_arguments:
  - tag_id
  required:
  - tag_id
- name: tag_entity
  category: tags
  description: Apply a workspace tag to an entity. The tag must already exist (use create_tag first).
  input_arguments:
  - entity_id
  - entity_type
  - tag_id
  required:
  - entity_id
  - entity_type
  - tag_id
- name: untag_entity
  category: tags
  description: Remove a workspace tag from an entity.
  input_arguments:
  - entity_id
  - entity_type
  - tag_id
  required:
  - entity_id
  - entity_type
  - tag_id
- name: list_entity_tags
  category: tags
  description: List all tags applied to a specific entity.
  input_arguments:
  - entity_id
  - entity_type
  required:
  - entity_id
  - entity_type
- name: list_data_classes
  category: sensitivity
  description: List data classification categories configured in Bigeye.
  input_arguments:
  - page_cursor
  - page_size
  - search
  - sensitivities
  required: []
- name: get_table_sensitivity_findings
  category: sensitivity
  description: Get sensitive data scan findings for a specific table by name.
  input_arguments:
  - finding_type
  - page_cursor
  - page_size
  - positive_only
  - schema_name
  - sensitivities
  - table_name
  required:
  - table_name
- name: get_scan_findings
  category: sensitivity
  description: Get data classification scan findings from Bigeye using raw IDs.
  input_arguments:
  - column_ids
  - data_class_ids
  - finding_type
  - page_cursor
  - page_size
  - positive_only
  - search
  - sensitivities
  - table_ids
  required: []
crosswalk: mcp/bigeye-tool-crosswalk.yml