API Docs MCP

Created By
EliFuzz7 months ago
MCP server for API documentation, supporting GraphQL, OpenAPI/Swagger, and gRPC from local files or remote URLs
Overview

what is API Docs MCP?

API Docs MCP is a server that provides tools for interacting with API documentation, supporting various specifications like GraphQL, OpenAPI/Swagger, and gRPC from local files or remote URLs.

how to use API Docs MCP?

To use API Docs MCP, set the API_SOURCES environment variable with the desired API specifications and run the command API_SOURCES={API_SOURCES} npx api-docs-mcp to start the server.

key features of API Docs MCP?

  • Dynamic Tool Registration: Automatically discovers and registers tools from a specified directory.
  • API Documentation Retrieval: Tools to list available API methods and retrieve detailed documentation for specific methods.
  • Schema Caching: Caches API schema information to improve performance.
  • Multiple Source Support: Supports GraphQL, OpenAPI/Swagger, and gRPC schemas from various sources.
  • Environment-based Configuration: Configures API sources via the API_SOURCES environment variable.
  • Automatic Cache Refresh: Periodically refreshes cached schema data.

use cases of API Docs MCP?

  1. Managing and documenting APIs for software development.
  2. Fetching and caching API schemas for improved performance.
  3. Supporting multiple API specifications in a single server environment.

FAQ from API Docs MCP?

  • What API specifications does API Docs MCP support?

It supports GraphQL, OpenAPI/Swagger, and gRPC specifications.

  • How do I configure API sources?

You can configure API sources using the API_SOURCES environment variable.

  • Is API Docs MCP suitable for production use?

Yes, it is designed for flexible deployment and management of API documentation.

Server Config

{
  "mcpServers": {
    "api-docs-mcp": {
      "command": "npx",
      "args": [
        "api-docs-mcp"
      ],
      "env": {
        "API_SOURCES": "[{\"name\": \"PetstoreAPI\", \"method\": \"GET\", \"url\": \"https://petstore.swagger.io/v2/swagger.json\", \"type\": \"api\"}]"
      }
    }
  }
}
Project Info
Created At
7 months ago
Updated At
7 months ago
Author Name
EliFuzz
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago