governance-hub
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.
Descriptor
Candidate descriptor · transport stdio
Tools
get_catalog_overview— Confirm MCP connection and check whether vector search over the Credo AI Governance Intelligence catalog is available.governance_query— Semantic/keyword search across the Governance Intelligence catalog for risks, controls and policy requirements.get_entities— Fetch full catalog records for the top matches returned by governance_query. Required before scoring — the plugin documentation warns that truncated descriptions produce wrong risk scores.get_maturity_framework— The versioned Credo AI maturity framework — five bands (Exploring through Speed & Scale), six domains (Risk & Governance, Use Case Inventory, Policy & Compliance, Executive Sponsorship, Technical Controls, Vendor & Third-Party AI), four-criteria ladders per domain, scoring rules and the canonical report structure. Returns framework.version, which assessments must record.get_benchmarks— Vetted, sourced benchmark claims by industry segment. An empty response means the benchmarks section is omitted — the skill is explicitly instructed never to invent statistics.
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.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.