OpenAPI to MCP
Turning existing API specs into MCP tools. As of 2026-11-21, 19 indexed products offer it (14 with full profiles), in 2 forms: 17 MCP servers, 2 Agent skills. 13 were published in the last 90 days, against 2 in the 90 days before. AnythingMCP has the most GitHub stars, 55% of the total across 13 products with their own repository.
CapabilitySegment label: Emerging DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 17 indexed · 12 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | AnythingMCPMCP gateway and company brain: 957 connectors (SAP, ERP, SQL), file search, memory and skills. | HelpCode-ai | 815 | today | ||
| 2 | mcp-linkConvert Any OpenAPI V3 API to MCP Server | automation-ai-labs | 625 | 1y ago | ||
| 3 | surfPoint Gecko at an OpenAPI spec; get first-call-correct, auth-hidden agent tools. | geckovision.tech | 22 | 1mo ago | ||
| 4 | jitapiTurn any OpenAPI spec into an executable agent interface using graphs and semantic search. | nk3750 | 7 | 5mo ago | ||
| 5 | WranglTurn any REST API into MCP tools, from an OpenAPI spec, a Postman collection, or a base URL. | asgerami | 4 | 9d ago | ||
| 6 | app-store-connect-mcpMCP server for Apple's App Store Connect API: 1316 tools generated from the official OpenAPI spec. | devinwang | 3 | 1mo ago | ||
| 7 | API ShakedownTurn an OpenAPI spec into WireMock stubs, contract tests and chaos scenarios, on local LLMs. | anzar-ahsan-commits | 2 | 1d ago | ||
| 8 | JiZhiMCPHost any HTTP API as MCP tools with a tamper-evident cross-agent settlement ledger. | xn--5kvtwv52d.com | 1 | 3d ago | ||
| 9 | mcp-gateway (OpenAPI to MCP)OpenAPI or local API to MCP server, with a public HTTPS tunnel. Rust CLI, any MCP client. | Fetch-Hive | 1 | 11d ago | ||
| 10 | mockanythingLocal, stateful twins of any API (Stripe, Twilio, any OpenAPI spec) for agents. No keys, no bill. | shreyassaw5394 | 1 | 8d ago |
Agent skills 2 indexed · 2 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | api-breaking-change-detectorCross-references C# Web API controllers/DTOs against their TypeScript/JavaScript consumers (React, Angular, Vue, Svelte, Node.js, or hand-written/auto-generated HTTP clients like Fetch, Axios, NSwag) to catch contract drift in both directions: backend changes that break client applications (renamed/removed JSON keys, new required parameters, status code shifts) and frontend code sending fields the backend no longer reads. Works directly against source code, not exported OpenAPI spec files. Use when the user asks to check for breaking API changes, verify frontend/backend contract sync, or audit a DTO/controller change against its TypeScript/JS consumers before merging. Not for generating new API code from a spec (see openapi-to-application-code) or scaffolding new endpoints (see aspnet-minimal-api-openapi). | github | — | 1d ago | ||
| 2 | cli-creatorBuild a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill. | openai | — | 24d ago |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 17 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 2 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Codex | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| openapi to mcp | 2 |
| openapi spec | 14 |
| swagger to mcp | 0 |
| api to mcp | 3 |
| convert openapi | 0 |
| generate mcp server | 0 |
Segment statistics
Whole catalogue (19 indexed products). Calculated 2026-11-21.
Emerging. Among the smallest 30% of capabilities, but launches are outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.481 means stars are spread as if across about 2 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .