MCP
MCP is a directory of Model Context Protocol (MCP) servers, providing a searchable list of AI tool integrations such as Claude, ChatGPT, Cursor, and VS Code extensions. It lists over 1,500 servers, each with detailed pages describing capabilities, setup commands, and sign‑in requirements. The service is run by Marco Costantino in Italy and does not host, audit, or vouch for the listed servers. Users can submit servers without an account, and the platform offers Markdown outputs for machine consumption, a CLI, and a blog for updates.
MCP publishes 3 API contracts indexed on the APIs.io network: Directory API, Registry API, and Submit API. Tagged areas include Directory, Artificial Intelligence, Tools, Open Source, and Community.
The MCP catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.
MCP’s developer surface includes CLI, changelog, authentication, documentation, engineering blog, getting-started guide, API reference, and 25 more developer resources.
Kin Score
Standards implemented 2
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
APIs 3
Individual APIs this provider publishes, each with its own machine-readable definition.
MCP Directory API
mcp.tc's own formats: search index, listing JSON and Markdown, change feeds.
MCP Registry API
MCP-Registry-compatible read API (official openapi v0.1).
MCP Submit API
Suggest a server for the directory from a script, then follow its status.
MCP Servers 1
Model Context Protocol servers that expose these APIs to AI agents.
Agent Skills 1
Packaged agent skills for driving this provider's APIs from an AI assistant.
get-health
AGENT SKILLSemantic Vocabularies 1
JSON-LD contexts and semantic vocabularies used across these APIs.
Mcp Tc Context
JSON-LDSpectral Rules 1
Spectral governance rulesets for linting and validating these APIs. Counts are the severity each rule declares, not results of running them.
MCP API Rules
SPECTRALJSON Schema 6
Standalone JSON Schema definitions for this provider's data models.
IndexEntry
JSON SCHEMAListingJson
JSON SCHEMASubmissionStatus
JSON SCHEMASubmitAccepted
JSON SCHEMASubmitDuplicate
JSON SCHEMASubmitRequest
JSON SCHEMASecurity Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access (API Evangelist recommendations) 1
Recommended x-agentic-access execution contracts for AI agents.
Resources
Get Started 1
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 5
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 7
Pagination, idempotency, versioning, errors, and events
Scroll for all 7
Build 4
SDKs, sample code, and the tooling you integrate with
Access & Security 5
Authentication, authorization, and security posture
Operate 2
Status, limits, changes, and where to get help
Commercial 2
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 2
Properties that don't map to a standard resource type
Source (apis.yml)
MCP API — frequently asked questions
Does MCP have an API?
Yes. APIs.io lists 3 APIs from MCP, including MCP Directory API, MCP Registry API and MCP Submit API.
Is there an OpenAPI specification for the MCP API?
Yes. APIs.io indexes 3 OpenAPI specifications for MCP, each linked for download from this page.
How do I authenticate with the MCP API?
MCP uses bearer-token authentication (1 scheme). The details are profiled on APIs.io as MCP Authentication.
Does MCP have an MCP server?
Yes. APIs.io lists 1 MCP server for MCP: Remote MCP server at mcp.tc.
Is the MCP API ready for AI agents?
MCP has a Kin Score of 48.1 out of 100 (developing) and an Agent Readiness score of 36.9 (agent-ready), scored by API Evangelist on 2026-11-21.
Work with this as data
Every provider here is available over the APIs.io API and to AI agents over MCP.