Turn any OpenAPI/Swagger spec into MCP tools — so Claude and other AI assistants can call your REST APIs.
Point mcp-openapi at any OpenAPI 3.x or Swagger 2.0 spec URL and it generates Model Context Protocol (MCP) tools automatically. No code generation, no config files, no boilerplate. Your AI assistant gets callable tools for every API endpoint in seconds.
1. Run it (no install required):
npx mcp-openapi --spec https://petstore3.swagger.io/api/v3/openapi.json2. Add it to Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"petstore": {
"command": "npx",
"args": [
"mcp-openapi",
"--spec", "https://petstore3.swagger.io/api/v3/openapi.json"
]
}
}
}3. Ask Claude to use it:
"List all available pets in the store"
Claude sees MCP tools like find_pets_by_status, get_pet_by_id, add_pet and calls them directly.
Most MCP-to-API bridges require you to write tool definitions by hand or generate code from a spec. mcp-openapi skips all of that.
| Feature | mcp-openapi | Hand-written MCP servers | Generic HTTP tools |
|---|---|---|---|
| Zero config setup | Yes | No | Partial |
| OpenAPI 3.x + Swagger 2.0 | Yes | N/A | N/A |
| Flat parameter schemas (LLM-optimized) | Yes | Manual | No |
| Smart tool naming from operationId | Yes | Manual | No |
| Auth (API key, Bearer, OAuth2) | Built-in | DIY | DIY |
| Retry with exponential backoff | Built-in | DIY | DIY |
| Response truncation for LLM context | Built-in | DIY | No |
Flat parameter schemas are the key differentiator. Instead of passing nested JSON objects (which LLMs frequently get wrong), mcp-openapi flattens path, query, header, and body parameters into a single flat object. This dramatically improves tool-calling accuracy.
OpenAPI/Swagger Spec mcp-openapi AI Assistant
(URL or file) (Claude, etc.)
| | |
| 1. Parse & validate | |
|------------------------>| |
| | |
| 2. Generate MCP tools | |
| (one per endpoint) | |
|------------------------>| |
| | |
| | 3. Register tools |
| | via stdio transport |
| |------------------------>|
| | |
| | 4. AI calls a tool |
| |<------------------------|
| | |
| 5. Build & execute | |
| HTTP request | |
|<------------------------| |
| | |
| 6. Return truncated | |
| response to AI | |
|------------------------>|------------------------>|
Each API endpoint becomes one MCP tool:
- Tool name is derived from
operationId(converted tosnake_case) or frommethod + path - Parameters are flattened into a single input schema (path, query, header, and body params merged)
- Responses are truncated to ~50KB to stay within LLM context limits
- Errors (429, 5xx) trigger automatic retries with exponential backoff (up to 3 retries)
Add any API to Claude Desktop by editing your config file:
Location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"petstore": {
"command": "npx",
"args": [
"mcp-openapi",
"--spec", "https://petstore3.swagger.io/api/v3/openapi.json"
]
}
}
}{
"mcpServers": {
"github": {
"command": "npx",
"args": [
"mcp-openapi",
"--spec", "https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json",
"--auth-type", "bearer",
"--auth-token", "$GITHUB_TOKEN",
"--prefix", "github",
"--include", "listReposForAuthenticatedUser,getRepo,listIssues,createIssue"
],
"env": {
"GITHUB_TOKEN": "ghp_your_token_here"
}
}
}
}{
"mcpServers": {
"weather": {
"command": "npx",
"args": [
"mcp-openapi",
"--spec", "https://api.weather.example.com/openapi.json",
"--auth-type", "api-key",
"--auth-name", "X-API-Key",
"--auth-value", "$WEATHER_API_KEY",
"--auth-in", "header"
],
"env": {
"WEATHER_API_KEY": "your_key_here"
}
}
}
}npx mcp-openapi --spec <url-or-path> [options]| Option | Short | Default | Description |
|---|---|---|---|
--spec <url|path> |
-s |
required | OpenAPI spec URL or local file path |
--config <path> |
-c |
JSON config file path | |
--base-url <url> |
from spec | Override the API base URL | |
--prefix <name> |
Prefix for all tool names (e.g. github -> github_list_repos) |
||
--include <patterns> |
all | Comma-separated operationIds to include | |
--exclude <patterns> |
none | Comma-separated operationIds to exclude | |
--timeout <ms> |
30000 |
HTTP request timeout in milliseconds | |
--max-retries <n> |
3 |
Max retries on 429/5xx responses | |
--header <name:value> |
-H |
Custom header (repeatable) | |
--transport <type> |
stdio |
Transport type: stdio or sse |
|
--port <n> |
3000 |
Port for SSE transport | |
--help |
-h |
Show help | |
--version |
-v |
Show version | |
--license-key <key> |
Pro license key (or $MCP_OPENAPI_LICENSE_KEY env) |
||
--server <selector> |
0 |
Select API server by index, partial URL, or exact URL | |
--no-doc-warnings |
Suppress doc quality warnings on startup | ||
--dynamic-discovery |
auto (100+) | Enable dynamic tool discovery for large APIs |
Bearer token:
| Option | Description |
|---|---|
--auth-type bearer |
Use Bearer token authentication |
--auth-token <token> |
The token value (supports $ENV_VAR syntax) |
API key:
| Option | Description |
|---|---|
--auth-type api-key |
Use API key authentication |
--auth-name <name> |
Header or query parameter name |
--auth-value <value> |
The API key value (supports $ENV_VAR syntax) |
--auth-in <header|query> |
Where to send the key (default: header) |
OAuth2 client credentials:
| Option | Description |
|---|---|
--auth-type oauth2 |
Use OAuth2 client credentials flow |
--auth-client-id <id> |
OAuth2 client ID |
--auth-client-secret <secret> |
OAuth2 client secret |
--auth-token-url <url> |
Token endpoint URL |
--auth-scopes <scopes> |
Comma-separated scopes |
# Basic usage with a remote spec
npx mcp-openapi --spec https://petstore3.swagger.io/api/v3/openapi.json
# Local YAML spec with Bearer auth
npx mcp-openapi --spec ./api.yaml --auth-type bearer --auth-token '$API_KEY'
# Filter to specific endpoints with a prefix
npx mcp-openapi --spec ./api.json --prefix myapi --include 'listUsers,getUser'
# Override base URL (useful for local dev)
npx mcp-openapi --spec https://api.example.com/openapi.json --base-url http://localhost:3000
# Add custom headers
npx mcp-openapi --spec ./api.json -H 'X-Custom: value' -H 'X-Another: value2'
# Use a JSON config file
npx mcp-openapi --config ./mcp-config.json
# Select staging server
npx mcp-openapi --spec ./api.json --server staging
# Large API with dynamic discovery
npx mcp-openapi --spec https://api.stripe.com/openapi.json --dynamic-discoveryInstead of CLI flags, you can use a JSON config file:
{
"spec": "https://api.example.com/openapi.json",
"prefix": "myapi",
"include": ["listUsers", "getUser", "createUser"],
"auth": {
"type": "bearer",
"token": "$API_TOKEN"
},
"timeout": 15000,
"maxRetries": 2,
"headers": {
"X-Custom-Header": "value"
}
}CLI arguments take precedence over config file values.
| Format | Versions | File types |
|---|---|---|
| OpenAPI | 3.0.x, 3.1.x | .json, .yaml, .yml |
| Swagger | 2.0 | .json, .yaml, .yml |
Specs can be loaded from:
- Remote URLs (
https://...) - Local file paths (
./api.yaml,/absolute/path/spec.json)
On startup, mcp-openapi checks each tool's documentation quality. If endpoints have sparse descriptions (under 50 characters), you'll see a warning:
[mcp-openapi] WARN: Doc quality: 11 of 47 tools have sparse documentation (<50 chars)
[mcp-openapi] WARN: Affected: getUser, createOrder, deleteItem, updateCart, listTags, ...
[mcp-openapi] WARN: LLM accuracy may be reduced for these endpoints.
This helps you identify which API endpoints might cause poor LLM tool-calling accuracy. Suppress with --no-doc-warnings.
OpenAPI specs can define multiple servers (production, staging, dev). Select which one to use:
# Use first server (default behavior)
mcp-openapi --spec api.json --server 0
# Match by URL keyword
mcp-openapi --spec api.json --server prod
# Exact URL
mcp-openapi --spec api.json --server https://api.example.com/v2If the selector doesn't match, you'll see all available servers listed.
For large APIs with 100+ endpoints, registering all tools at once can overwhelm the LLM's context. Dynamic discovery solves this by registering 3 meta-tools instead:
| Meta-tool | Description |
|---|---|
search_operations(query) |
Search tools by keyword in names, descriptions, and tags |
list_by_tag(tag?) |
Browse tools by OpenAPI tag, or list all tags |
get_tool_details(tool_name) |
Get full parameter schema for a specific tool |
The LLM explores the API through these meta-tools, then calls specific endpoints by name.
# Explicit opt-in
mcp-openapi --spec large-api.json --dynamic-discovery
# Auto-enabled when spec has 100+ endpoints
mcp-openapi --spec https://api.github.com/openapi.jsonOr via config file:
{
"spec": "https://api.stripe.com/openapi.json",
"dynamicDiscovery": true,
"auth": { "type": "bearer", "token": "$STRIPE_KEY" }
}mcp-openapi includes optional Pro features for teams and power users, gated by a license key.
Shape API responses with JMESPath expressions before they reach the LLM — reducing token usage and improving accuracy:
{
"spec": "https://api.github.com/openapi.json",
"licenseKey": "$MCP_OPENAPI_LICENSE_KEY",
"transforms": {
"list_repos": "data[].{name: name, stars: stargazers_count, url: html_url}",
"list_*": "data[].{id: id, name: name}"
}
}Instead of hard-truncating large responses at 50KB, Pro enables intelligent truncation:
- Array slicing: Large arrays show first N items + metadata (
"showing 10 of 847 items") - Depth pruning: Deep nested objects are summarized beyond a configurable depth
- Structure preservation: You always see the shape of the data, never a mid-JSON cut
{
"spec": "./api.json",
"licenseKey": "$MCP_OPENAPI_LICENSE_KEY",
"response": {
"maxLength": 50000,
"arraySliceSize": 10,
"maxDepth": 4
}
}- Multi-API Composition — Load multiple OpenAPI specs into one MCP session
- Usage Analytics — Track tool calls, latency, and error rates
Interested in Pro? Star the repo and open an issue to get early access.
You can also use mcp-openapi as a library in your own MCP server:
import { createServer } from 'mcp-openapi';
const { server, tools, spec } = await createServer({
spec: 'https://petstore3.swagger.io/api/v3/openapi.json',
prefix: 'petstore',
auth: {
type: 'bearer',
token: process.env.API_TOKEN,
},
});
console.log(`Loaded ${tools.length} tools from ${spec.info.title}`);- Node.js 18 or later
- An OpenAPI 3.x or Swagger 2.0 spec (URL or local file)
Contributions are welcome. Here is how to get started:
git clone https://github.com/Docat0209/mcp-openapi.git
cd mcp-openapi
pnpm install
pnpm test
pnpm buildBefore submitting a PR:
- Add tests for new features
- Run
pnpm lintand fix any issues - Follow Conventional Commits for commit messages
- graphql-to-mcp — Same zero-config approach for GraphQL APIs
MIT
mcp, model-context-protocol, openapi, swagger, claude, ai, llm, api, tools, rest-api, ai-tools, mcp-server