whatisgithub

What is omnimcp?

doppler2u/omnimcp — explained in plain English

Analysis updated 2026-05-18

★ 0TypeScriptAudience · developerComplexity · 3/5LicenseSetup · moderate

In one sentence

OmniMCP reads an existing web API's OpenAPI or Swagger spec and automatically generates an MCP style agent interface for it, so AI agents can call the API directly.

Mindmap

mindmap
  root((OmniMCP))
    What it does
      Reads OpenAPI Swagger specs
      Generates MCP agent surface
      AI powered endpoint mapping
      Proxies calls to real API
    Tech stack
      TypeScript
      Next.js
      React
      OpenRouter Gemini
    Use cases
      Agent to agent API access
      Pay per call monetization
      Hackathon demo tooling
    Extras
      JSON RPC endpoint
      Interactive tool tester
      On chain schema hash

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Turn an existing REST API's OpenAPI or Swagger spec into a callable MCP agent tool without writing integration code by hand.

USE CASE 2

Let one AI agent call another service's API through a generated JSON-RPC tools/call endpoint.

USE CASE 3

Prototype a pay-per-call, agent-to-agent marketplace listing for an existing web API.

USE CASE 4

Test a newly generated agent's tools through an interactive form-based UI.

What is it built with?

TypeScriptNext.jsReactTailwind CSSOpenRouter

How does it compare?

doppler2u/omnimcp0xkinno/astraea0xkinno/halcyon
Stars000
LanguageTypeScriptTypeScriptTypeScript
Setup difficultymoderatehardhard
Complexity3/54/54/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires Node.js 18+ and a free OpenRouter API key to power the AI-based endpoint mapping.

MIT license: free to use, modify, and distribute, including commercially, as long as the license text is kept.

So what is it?

OmniMCP was built for the OKX.AI Genesis Hackathon and aims to solve a specific onboarding problem for AI agent marketplaces. Many useful services already exist as ordinary web APIs, described by an OpenAPI or Swagger specification, but AI agents typically need a different kind of interface called MCP to talk to tools automatically. OmniMCP reads an existing API's specification and automatically generates a working MCP style agent surface for it, so that an old web API can be plugged into an agent economy without anyone hand writing integration code. The tool fetches and normalizes OpenAPI 3.x or Swagger 2.0 specifications, then uses an AI model, specifically Gemini 2.5 Flash through OpenRouter, to translate each REST endpoint into a clearly described tool definition that other AI agents can understand and call. Once generated, each agent exposes a JSON-RPC endpoint with methods for listing available tools and calling them, letting one AI agent invoke another agent's underlying API through this generated layer. Behind the scenes, a proxy engine intercepts these calls, rebuilds the correct HTTP request to the original API, and returns the result. The project also wires in monetization and verification pieces tied to the OKX.AI ecosystem: generated tools can be wrapped so each call is billed through a pay per call protocol, and the schema of each agent gets a cryptographic hash computed for verification on a blockchain called X Layer. For the hackathon demo itself, the app includes a fallback mode that swaps in prewritten example responses if the AI service is temporarily overloaded, so the live demonstration keeps working. Running it locally requires Node.js 18 or newer and a free OpenRouter API key. It stores generated agents in local files rather than a database, so no separate setup is needed to try it out. The project is released under the MIT license.

Copy-paste prompts

Prompt 1
Walk me through setting up OmniMCP locally with an OpenRouter API key and generating my first MCP agent from a sample OpenAPI spec.
Prompt 2
Explain how OmniMCP's proxy engine maps an MCP tool call back into the original REST API request.
Prompt 3
How do I add API key or bearer token credentials to an API I'm onboarding into OmniMCP?
Prompt 4
Show me the JSON-RPC request format for calling a generated agent's tools/list and tools/call methods.

Frequently asked questions

What is omnimcp?

OmniMCP reads an existing web API's OpenAPI or Swagger spec and automatically generates an MCP style agent interface for it, so AI agents can call the API directly.

What language is omnimcp written in?

Mainly TypeScript. The stack also includes TypeScript, Next.js, React.

What license does omnimcp use?

MIT license: free to use, modify, and distribute, including commercially, as long as the license text is kept.

How hard is omnimcp to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is omnimcp for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.

What are similar repos?