conviva-mcp.yml
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/.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
identity-c3-account-list— List the c3 accounts the caller is authorized for. Account-scoped tools require an explicit c3AccountName; there is no safe default.context-center-nexa-semantic-search— 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.context-center-nexa-categories-list— List the valid knowledge categories (asset types) usable for scoping semantic search.context-center-nexa-knowledge-get— Fetch a knowledge entry by its k_* id — the reverse lookup from an asset's knowledge_id.context-center-asset-get— Hydrate the authoritative structured definition of one Context Center asset by assetType + assetId (pattern, metric, critical-event, dimension, segment, template).context-center-asset-list— Page through all assets of an assetType, returning { items, pagination }. The search argument filters one already-fetched page, not the whole result set.metric-query-run— 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.nexa-analyze— 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).nexa-analyze-result— Retrieve the result of an async nexa-analyze job. Backed by a Redis job store.insights-behavior-segment-list— List Insights behavior segments (formerly "patterns") by name.insights-behavior-segment-get— 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.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.