@minamorl/openapi-mcp-bridge
Runtime MCP server that dynamically bridges any OpenAPI 3.x spec to MCP tools.
README
@minamorl/openapi-mcp-bridge
Runtime MCP server that dynamically bridges any OpenAPI 3.x spec to MCP tools.
No code generation. No build step. One command.
Quick Start
npx @minamorl/openapi-mcp-bridge --spec https://petstore3.swagger.io/api/v3/openapi.json
Why not codegen?
Existing tools (openapi-mcp-generator, etc.) generate static TypeScript files from your OpenAPI spec. Every time the API changes, you regenerate, rebuild, redeploy.
openapi-mcp-bridge takes a different approach: runtime bridging. It reads the OpenAPI spec at startup and dynamically creates MCP tools. Update the spec → restart the server. That's it.
| Codegen tools | openapi-mcp-bridge | |
|---|---|---|
| API spec changes | Regenerate → rebuild → restart | Restart only |
| Setup | npm install → generate → configure → build → start | npx + 1 flag |
| OAuth2 | "Put token in .env" | Built-in auth flows |
| Transport | stdio only | stdio + Streamable HTTP (planned) |
Usage
CLI
# From URL
openapi-mcp-bridge --spec https://api.example.com/openapi.json
# From local file (JSON or YAML)
openapi-mcp-bridge --spec ./api.yaml
# With auth
openapi-mcp-bridge --spec ./api.yaml --auth-type bearer --auth-token $TOKEN
# With custom base URL
openapi-mcp-bridge --spec ./api.yaml --base-url http://localhost:3000
# With custom headers
openapi-mcp-bridge --spec ./api.yaml -H "X-Custom: value"
Claude Desktop / Cursor config
{
"mcpServers": {
"my-api": {
"command": "npx",
"args": ["@minamorl/openapi-mcp-bridge", "--spec", "https://api.example.com/openapi.json"]
}
}
}
Programmatic API
import { parseSpec, createBridgeServer, startStdioServer } from "@minamorl/openapi-mcp-bridge";
const doc = await parseSpec("./api.yaml");
const server = await createBridgeServer({ doc, baseUrl: "http://localhost:3000" });
await startStdioServer(server);
How It Works
OpenAPI 3.x spec (JSON/YAML/URL)
↓ Parse + resolve $refs
Tool definitions (name, schema, method, path)
↓ Register as MCP tools
MCP Server (stdio)
↓ On tool call
HTTP request to actual API
↓
Response back to LLM
- Parser reads and validates the OpenAPI spec, resolving all
$refreferences - Mapper converts each operation to an MCP tool with proper input schemas
- Server registers tools and handles MCP protocol
- Executor translates tool calls into HTTP requests
Auth
# Bearer token
--auth-type bearer --auth-token YOUR_TOKEN
# API key
--auth-type api-key --auth-token YOUR_KEY --api-key-header X-API-Key
# Basic auth (token = base64 of user:pass)
--auth-type basic --auth-token BASE64_CREDENTIALS
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.