mcp-openapi-runner
Turn any OpenAPI spec into MCP tools for Claude — instantly. Point mcp-openapi at any OpenAPI 3.x spec and Claude can call every endpoint through natural language. No custom integration code. No manual tool definitions. One line of config.
README
mcp-openapi
Turn any OpenAPI spec into MCP tools for Claude — instantly.
Point mcp-openapi at any OpenAPI 3.x spec and Claude can call every endpoint through natural language. No custom integration code. No manual tool definitions. One line of config.
Quick start
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"my-api": {
"command": "npx",
"args": ["-y", "mcp-openapi", "--spec", "https://petstore3.swagger.io/api/v3/openapi.json"]
}
}
}
That's it. Claude can now discover and call every endpoint in that API.
Example conversation
You: What pets are available, and add a new dog named Buddy
Claude: Let me check what's available first. [calls
list_endpoints→ seesfindPetsByStatus,addPet, etc.] [callscall_endpointwithfindPetsByStatus,status=available]There are 3 pets currently available. Now I'll add Buddy... [calls
call_endpointwithaddPet, body{"name":"Buddy","status":"available"}]Done! Buddy has been added with ID 12345.
Authentication
Pass credentials via environment variables:
{
"mcpServers": {
"my-api": {
"command": "npx",
"args": ["-y", "mcp-openapi", "--spec", "https://api.example.com/openapi.json"],
"env": {
"OPENAPI_BEARER_TOKEN": "your-token-here"
}
}
}
}
| Variable | Description |
|---|---|
OPENAPI_BEARER_TOKEN |
Bearer token → Authorization: Bearer <token> |
OPENAPI_API_KEY |
API key value |
OPENAPI_API_KEY_HEADER |
Header name for API key (default: X-Api-Key) |
OPENAPI_BASIC_USER |
HTTP Basic auth username |
OPENAPI_BASIC_PASS |
HTTP Basic auth password |
Tools
mcp-openapi exposes exactly two tools:
| Tool | Description |
|---|---|
list_endpoints |
Returns all operations grouped by tag with operationIds, methods, paths, and required parameters |
call_endpoint |
Executes any operation by operationId with path/query/body parameters |
The two-tool design means Claude always has a clear workflow: discover → call.
Using a local spec file
{
"mcpServers": {
"my-api": {
"command": "npx",
"args": ["-y", "mcp-openapi", "--spec", "/path/to/your/openapi.yaml"]
}
}
}
Supports both JSON and YAML specs. All $ref references are resolved automatically.
Requirements
- Node.js 18+
- OpenAPI 3.x spec (JSON or YAML, local file or URL)
Real-world examples
Stripe API:
["--spec", "https://raw.githubusercontent.com/stripe/openapi/master/openapi/spec3.json"]
GitHub REST API:
["--spec", "https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json"]
Your internal API:
["--spec", "http://localhost:8080/openapi.json"]
CLI usage
# From URL
npx mcp-openapi --spec https://api.example.com/openapi.json
# From file
npx mcp-openapi --spec ./openapi.yaml
# With auth
OPENAPI_BEARER_TOKEN=mytoken npx mcp-openapi --spec https://api.example.com/openapi.json
# Help
npx mcp-openapi --help
How it works
- At startup, loads the spec from the given URL or file path
- Dereferences all
$refschemas using@apidevtools/swagger-parser - Registers two MCP tools with the connected client
list_endpointsgenerates a human+LLM-readable summary of all operationscall_endpointresolves path params, builds the URL, attaches auth headers, and returns the response
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.