snaggle-ai/openapi-mcp-server
by Various
Allow AI to wade through complex OpenAPIs using Simple Language
MCP
snaggle-ai/openapi-mcp-server
Added 1 June 2026
Overview
An open-source TypeScript server that translates complex OpenAPI specifications into a simplified interface for AI agents. It uses the Model Context Protocol (MCP) to let language models navigate and invoke API endpoints using natural language prompts.
Best for
Best for
Developers building AI agents that need to dynamically interact with REST APIs via natural language
Use cases
- Enable an AI assistant to call REST APIs from a natural language request
- Simplify integration of third-party APIs into AI workflows without manual endpoint mapping
- Prototype AI-driven automation that interacts with multiple OpenAPI-based services
How to use
Install
wrangler dev Tools exposed
@modelcontextprotocol/inspectorwrangler
Tested with
Claude Desktop, Cursor
Notes
An open-source TypeScript server that translates complex OpenAPI specifications into a simplified interface for AI agents. It uses the Model Context Protocol (MCP) to let language models navigate and invoke API endpoints using natural language prompts.
894 stars on GitHub. Last updated 2026-02-21. Licensed MIT.
Use cases
- Enable an AI assistant to call REST APIs from a natural language request
- Simplify integration of third-party APIs into AI workflows without manual endpoint mapping
- Prototype AI-driven automation that interacts with multiple OpenAPI-based services
Pros
- Reduces the need for developers to hand-code API call logic for AI agents
- Actively maintained with nearly 900 GitHub stars and TypeScript codebase
- Works with any OpenAPI-compliant API, offering broad compatibility
Cons
- Requires running a local or hosted MCP server, adding infrastructure overhead
- Performance depends on the complexity and size of the OpenAPI spec being processed
- Limited to APIs that expose a valid OpenAPI specification
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Reduces the need for developers to hand-code API call logic for AI agents
- Actively maintained with nearly 900 GitHub stars and TypeScript codebase
- Works with any OpenAPI-compliant API, offering broad compatibility
Cons
- Requires running a local or hosted MCP server, adding infrastructure overhead
- Performance depends on the complexity and size of the OpenAPI spec being processed
- Limited to APIs that expose a valid OpenAPI specification
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Computer Use
Anthropic
Claude takes the mouse and keyboard. A vision-based agent that controls a real desktop, not just a browser.
Continue
Continue.dev
Open-source AI code assistant for VS Code and JetBrains. Customisable, BYO model, built for enterprise.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.