OpenAPI Semantic Search

v1.0.0APIsstable

A MCP server that enables Claude to discover and call any API endpoint through semantic search. Intelligently chunks OpenAPI specifications to handle large API documentation, with built-in request execution capabilities. Perfect for integrating priva

faissmcp-serveropenapisemantic-search
Share:
82
Stars
0
Downloads
0
Weekly
0/5

What is OpenAPI Semantic Search?

OpenAPI Semantic Search is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that enables claude to discover and call any api endpoint through semantic search. intelligently chunks openapi specifications to handle large api documentation, with built-in request execu...

A MCP server that enables Claude to discover and call any API endpoint through semantic search. Intelligently chunks OpenAPI specifications to handle large API documentation, with built-in request execution capabilities. Perfect for integrating priva

This server falls under the APIs and Developer Tools categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A MCP server that enables Claude to discover and call any AP

Use Cases

Discover and call any API endpoint through semantic search of OpenAPI specs.
Execute API requests directly within Claude using intelligent chunking for large APIs.
baryhuang

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMar 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-server-scalable-openapi-endpoint-discovery-and-api-request-tool

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use OpenAPI Semantic Search

This MCP server enables Claude and other AI assistants to discover and call any REST API endpoint by performing semantic search over OpenAPI specifications using FAISS vector indexing and MiniLM-L3 embeddings. It intelligently chunks large OpenAPI specs that would otherwise exceed context limits, and exposes two tools — one for finding the right endpoint via natural language queries and one for executing the actual HTTP request. Developers use it to integrate private or internal APIs into AI workflows without manually translating API documentation into tool definitions.

Prerequisites

  • Python 3.8 or higher, or Docker
  • An OpenAPI specification JSON file or URL for the API you want to expose
  • An MCP client such as Claude Desktop
  • Network access from the server to the API's base URL for request execution
1

Install via pip

Install the mcp-server-any-openapi package from PyPI. This installs the server and its dependencies including FAISS and the sentence-transformers library.

pip install mcp-server-any-openapi
2

Alternative: run with Docker

Pull and run the pre-built Docker image. This is the recommended approach if you want to avoid managing Python dependencies.

docker pull buryhuang/mcp-server-any-openapi:latest
docker run -e OPENAPI_JSON_DOCS_URL=https://your-api.com/openapi.json buryhuang/mcp-server-any-openapi:latest
3

Alternative: install via Smithery

Use the Smithery CLI to install and configure the server for Claude Desktop automatically.

npx -y @smithery/cli install @baryhuang/mcp-server-any-openapi --client claude
4

Set the OpenAPI spec URL

Set the OPENAPI_JSON_DOCS_URL environment variable to the JSON URL of your target API's OpenAPI specification. Optionally set MCP_API_PREFIX to namespace the generated tool names.

export OPENAPI_JSON_DOCS_URL=https://your-internal-api.example.com/openapi.json
export MCP_API_PREFIX=myapi
5

Configure Claude Desktop

Add the server to claude_desktop_config.json with the required environment variables. The server generates two tools dynamically based on the prefix you set.

6

Test endpoint discovery

Ask Claude to search for an endpoint using a natural language description. The any_openapi_api_request_schema tool will return matching endpoint specs from your OpenAPI doc.

OpenAPI Semantic Search Examples

Client configuration

Add this block to claude_desktop_config.json. Replace the OPENAPI_JSON_DOCS_URL with your actual API spec URL. Adjust MCP_API_PREFIX to avoid tool name collisions if you run multiple instances.

{
  "mcpServers": {
    "any-openapi": {
      "command": "python",
      "args": ["-m", "mcp_server_any_openapi"],
      "env": {
        "OPENAPI_JSON_DOCS_URL": "https://your-api.example.com/openapi.json",
        "MCP_API_PREFIX": "any_openapi",
        "GLOBAL_TOOL_PROMPT": "Use these tools to interact with the internal company API.",
        "API_REQUEST_BASE_URL": "https://your-api.example.com"
      }
    }
  }
}

Prompts to try

Once the server is running with your OpenAPI spec loaded, use these prompts to discover and call endpoints.

- "Find the endpoint for listing all users and show me the required parameters."
- "Search for an endpoint that creates a new order and execute it with test data."
- "What endpoints are available for managing products in this API?"
- "Call the endpoint to get prices for all available items."
- "Find and execute the endpoint that returns the current authenticated user's profile."

Troubleshooting OpenAPI Semantic Search

Server starts but returns 'no endpoints found' for every query

Verify that OPENAPI_JSON_DOCS_URL is accessible from the machine running the server. Test with curl: 'curl $OPENAPI_JSON_DOCS_URL'. If the spec is behind authentication, set API_REQUEST_BASE_URL and include the auth token in a GLOBAL_TOOL_PROMPT or project-level system prompt.

FAISS or sentence-transformers import errors on startup

Install the missing dependencies manually: 'pip install faiss-cpu sentence-transformers'. On Apple Silicon, use 'pip install faiss-cpu --no-binary faiss-cpu' if the prebuilt wheel is incompatible.

Tool names conflict when running multiple OpenAPI servers

Set a unique MCP_API_PREFIX for each server instance (e.g., 'github_api', 'stripe_api'). This prefixes both generated tool names, preventing collisions in the MCP client's tool registry.

Frequently Asked Questions about OpenAPI Semantic Search

What is OpenAPI Semantic Search?

OpenAPI Semantic Search is a Model Context Protocol (MCP) server that mcp server that enables claude to discover and call any api endpoint through semantic search. intelligently chunks openapi specifications to handle large api documentation, with built-in request execution capabilities. perfect for integrating priva It connects AI assistants to external tools and data sources through a standardized interface.

How do I install OpenAPI Semantic Search?

Follow the installation instructions on the OpenAPI Semantic Search GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with OpenAPI Semantic Search?

OpenAPI Semantic Search works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is OpenAPI Semantic Search free to use?

Yes, OpenAPI Semantic Search is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More APIs MCP Servers

Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-server-scalable-openapi-endpoint-discovery-and-api-request-tool": { "command": "npx", "args": ["-y", "mcp-server-scalable-openapi-endpoint-discovery-and-api-request-tool"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use OpenAPI Semantic Search?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides