Redocly Docs MCP Server
Redocly ships a Docs MCP server as a Realm feature and runs it on its own documentation site. The endpoint answers anonymously: tools/list returns two real tools and resources/list returns the published agent skill. The wire surface is deliberately narrow — a sandbox `execute` tool plus a `describe-tools` introspection tool — and the actual capability lives in eleven sandbox functions callable from inside `execute`.
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
execute— Run JavaScript in a sandbox against the documentation tools on the global `tools` object. No fetch, console, setTimeout, require or Node API — all I/O goes through `tools`.describe-tools— Return the exact TypeScript signatures of the sandbox tools available to `execute`.
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.