OpenAPI Semantic Search
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
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
Maintainer
Works with
Installation
Manual Installation
npx mcp-server-scalable-openapi-endpoint-discovery-and-api-request-toolConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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-openapiAlternative: 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:latestAlternative: 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 claudeSet 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=myapiConfigure 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.
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.
OpenAPI Semantic Search Alternatives — Similar APIs Servers
Looking for alternatives to OpenAPI Semantic Search? Here are other popular apis servers you can use with Claude, Cursor, and VS Code.
Kong
★ 43.4k🦍 The API and AI Gateway
API Mega List
★ 5.4kThis GitHub repo is a powerhouse collection of APIs you can start using immediately to build everything from simple automations to full-scale applications. One of the most valuable API lists on GitHub—period. 💪
Fetch
★ 5.4kFetch web content and convert to markdown for AI consumption
Fusio
★ 2.1kSelf-Hosted API Management for Builders
Korean Law
★ 1.8k국가법령정보MCP v4.0 | 법제처 41개 API → 17개 MCP 도구. 법령·판례·조례 검색 + LLM 환각 방지 인용검증 + 조문 영향 그래프(impact_map) + 시점 비교 자동 diff(time_travel) + 시민 5단계 실행 가이드(action_plan) | 41 Korean legal APIs → 17 MCP tools
RuleGo
★ 1.5k⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
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.
Set Up OpenAPI Semantic Search in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.