generated: '2026-08-01' method: searched status: published source: https://docs.conviva.ai/connect-data/mcp/ sources: - https://docs.conviva.ai/connect-data/mcp/ - https://docs.conviva.ai/api/ssd/conviva-connect/whats-new-conviva-mcp/ - https://github.com/Conviva/mcp-marketplace - https://mcp.conviva.com/mcp - https://dpi-mcp.conviva.com/mcp description: >- Conviva operates TWO hosted, remote-only Model Context Protocol servers. Neither can be run locally. Both are OAuth 2.1 protected resources implementing RFC 8414 + RFC 9728 discovery with dynamic client registration and PKCE (S256); mcp.conviva.com additionally accepts HTTP Basic with a Pulse API key pair for autonomous (non-interactive) agents. A live tools/list on both servers returns JSON-RPC error -32001 "Unauthorized" (HTTP 401), so tool input schemas require an authenticated introspection. The tool names below are NOT guessed — they are taken verbatim from Conviva's own published Agent Skills in github.com/Conviva/mcp-marketplace, mirrored in this repo under skills/. servers: - name: conviva-mcp transport: http url: https://mcp.conviva.com/mcp version: 1.0.0 environment: production docs: https://docs.conviva.ai/connect-data/mcp/ covers: VSI (video) and vDPI metrics, AI alerts, viewer sessions, KPI threshold definitions services: - path: /vsi/metrics server_name: mcp-server-video-metrics - path: /vsi/ai-alerts server_name: mcp-server-video-ai-alerts - path: /vsi/sessions server_name: mcp-server-video-sessions - path: /dpi/metrics server_name: mcp-server-dpi-metrics - path: /dpi/ai-alerts server_name: mcp-server-dpi-ai-alerts auth: types: [oauth2, http-basic] oauth: issuer: https://mcp.conviva.com authorization_endpoint: https://mcp.conviva.com/oauth/authorize token_endpoint: https://mcp.conviva.com/oauth/token registration_endpoint: https://mcp.conviva.com/oauth/register jwks_uri: https://mcp.conviva.com/.well-known/jwks.json grant_types: [authorization_code, refresh_token] code_challenge_methods: [S256] token_endpoint_auth_methods: [none] scopes: [openid, profile, email, conviva] basic: header: 'Authorization: Basic base64(client_id:client_secret)' credential_source: Pulse API Management page note: Used for autonomous agents; OAuth is recommended because it carries user authorization. probe: tools_list: 401 Unauthorized (JSON-RPC -32001) service_descriptor: 200 (GET https://mcp.conviva.com/mcp) health: 200 (GET https://mcp.conviva.com/health) - name: conviva-dpi-mcp transport: http url: https://dpi-mcp.conviva.com/mcp version: 1.1.0 environment: production docs: https://github.com/Conviva/mcp-marketplace covers: Context Center knowledge + assets, predefined metric execution, Nexa open-ended analysis, Insights behavior segments, session replay services: - path: /insights - path: /nexa - path: /context-center - path: /session-replay - path: /metric-query auth: types: [oauth2] identity_provider: Okta oauth: issuer: https://dpi-mcp.conviva.com authorization_endpoint: https://dpi-mcp.conviva.com/oauth/authorize token_endpoint: https://dpi-mcp.conviva.com/oauth/token registration_endpoint: https://dpi-mcp.conviva.com/oauth/register jwks_uri: https://dpi-mcp.conviva.com/.well-known/jwks.json grant_types: [authorization_code, refresh_token] code_challenge_methods: [S256] token_endpoint_auth_methods: [none] scopes: [openid, profile, email, conviva] probe: tools_list: 401 Unauthorized (JSON-RPC -32001) www_authenticate: 'Bearer realm="mcp", error="invalid_request", error_description="Missing or malformed Authorization header"' service_descriptor: 200 (GET https://dpi-mcp.conviva.com/mcp) health: 200 (GET https://dpi-mcp.conviva.com/health) distribution: claude_plugin_marketplace: repo: https://github.com/Conviva/mcp-marketplace marketplace_name: conviva plugin: conviva-dpi-mcp plugin_version: 1.1.1 display_name: Conviva DPI MCP category: data add: /plugin marketplace add Conviva/mcp-marketplace install: /plugin install conviva-dpi-mcp@conviva requires: Claude Code v2.1.143 or newer bundles_skills: [exploring-context-center, querying-predefined-metrics, retrieving-behavior-segment-details] note: >- "This repository is a published mirror. It is generated from Conviva's internal source of truth on each release — do not edit it directly." claude_desktop: connector_url: https://dpi-mcp.conviva.com/mcp manual_config: 'npx mcp-remote https://dpi-mcp.conviva.com/mcp (Node.js 18+)' cursor: config: '~/.cursor/mcp.json -> {"mcpServers":{"conviva":{"url":"https://dpi-mcp.conviva.com/mcp"}}}' note: Cursor gets the tools only; the companion skills are Claude-plugin-only. # Tool names published by Conviva in its own Agent Skills (skills/). inputSchema for each tool is # NOT reproduced here because tools/list is auth-gated — nothing about parameters is invented. tools: - name: identity-c3-account-list server: conviva-dpi-mcp category: identity description: List the c3 accounts the caller is authorized for. Account-scoped tools require an explicit c3AccountName; there is no safe default. input_schema: gated - name: context-center-nexa-semantic-search server: conviva-dpi-mcp service: /context-center category: discovery description: Vector/ANN semantic search over the Context Center knowledge layer; accepts a free-text query, optional exact-substring terms, and categories scoping; returns hits with a similarity score. input_schema: gated - name: context-center-nexa-categories-list server: conviva-dpi-mcp service: /context-center category: discovery description: List the valid knowledge categories (asset types) usable for scoping semantic search. input_schema: gated - name: context-center-nexa-knowledge-get server: conviva-dpi-mcp service: /context-center category: discovery description: Fetch a knowledge entry by its k_* id — the reverse lookup from an asset's knowledge_id. input_schema: gated - name: context-center-asset-get server: conviva-dpi-mcp service: /context-center category: definition description: Hydrate the authoritative structured definition of one Context Center asset by assetType + assetId (pattern, metric, critical-event, dimension, segment, template). input_schema: gated - name: context-center-asset-list server: conviva-dpi-mcp service: /context-center category: definition description: Page through all assets of an assetType, returning { items, pagination }. The search argument filters one already-fetched page, not the whole result set. input_schema: gated - name: metric-query-run server: conviva-dpi-mcp service: /metric-query category: query description: Run a predefined metric by metricId over a startDate/endDate window, optionally with a patternId and groupByDimensionIds. Accepts ids only — never raw SQL or a raw query payload. input_schema: gated - name: nexa-analyze server: conviva-dpi-mcp service: /nexa category: analysis description: Async open-ended analysis fallback for questions no predefined metric answers. Requires a fallbackReason (no_matching_metric, unsupported_breakdown, open_ended_analysis, multi_metric_or_comparison, metric_query_failed, other). input_schema: gated - name: nexa-analyze-result server: conviva-dpi-mcp service: /nexa category: analysis description: Retrieve the result of an async nexa-analyze job. Backed by a Redis job store. input_schema: gated - name: insights-behavior-segment-list server: conviva-dpi-mcp service: /insights category: insights description: List Insights behavior segments (formerly "patterns") by name. input_schema: gated - name: insights-behavior-segment-get server: conviva-dpi-mcp service: /insights category: insights description: Retrieve the stored details of one Insights behavior segment — its pre-computed insights, evidence and conversion barriers. A static lookup, not a live analytical query. input_schema: gated tool_coverage_note: >- These 11 tools are the ones Conviva names in its published skills, all on the dpi-mcp server. The mcp.conviva.com server's five sub-services (/vsi/metrics, /vsi/ai-alerts, /vsi/sessions, /dpi/metrics, /dpi/ai-alerts) are confirmed live and named, but their individual tool names are not published anywhere anonymous — they require an authenticated tools/list. Recorded as unknown rather than guessed. known_limits: session_replay: Service /session-replay is advertised in the dpi-mcp descriptor but no tool for it appears in the published skills. nexa_local_dev: nexa-analyze / nexa-analyze-result return 503 without a Redis job store. changelog: - date: '2026-03-03' entry: MCP access unified into a single endpoint. - date: '2025-10' entry: Agent-based MCP requests added. x-evidence: fetched: '2026-08-01' tools_list_http_status: 401 descriptor_http_status: 200