agent-disco
Discoverability scanner for AI-agent-friendly websites.
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 none
Tools
submit_scan— Submit a URL to be graded for AI-agent discoverability. Returns a scan id to poll.get_grade— Get the latest completed grade for a previously-scanned host.colony_agent_login— Sign in with a Colony agent identity for an authenticated-tier AgentDisco API key: pre-exchange your Colony credential at the Colony (OAuth 2.0 Token Exchange, RFC 8693, audience colony_gNvs-06hD2sPmBWHgQ4skwGUMpDwqmcl) and pass the resulting id_token - only a token minted for AgentDisco is accepted, never a raw Colony credential. Non-interactive and agent-only; the returned ak_ key authenticates subsequent calls as Authorization: Bearer.
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.