Openapi Navigator
@mgaruccio
MCP server for handling large openapi specs
Overview
What is Openapi Navigator?
Openapi Navigator is an MCP server that makes OpenAPI specifications easily accessible to AI agents. It loads specs from local files or URLs and allows natural language searching of endpoints and schemas.
How to use Openapi Navigator?
Install the server with uvx openapi-navigator and add the JSON configuration to your MCP client settings. Once connected, use commands like load_spec, search_endpoints, and get_endpoint to explore and query OpenAPI specifications.
Key features of Openapi Navigator
- Load specs from local files or URLs (OpenAPI 3.x & Swagger 2.x)
- Smart search with fuzzy matching for endpoints and schemas
- Manage multiple API specifications simultaneously
- Preserves
$refstructures for agent decision-making - Fast indexing for instant lookups and searches
Use cases of Openapi Navigator
- API exploration – quickly understand API structure and capabilities
- Code generation – extract endpoint/schema info for automated code creation
- Documentation – generate comprehensive API documentation
- Integration planning – discover API features before implementation
- Testing – find endpoints and parameters for test automation
FAQ from Openapi Navigator
What OpenAPI versions does Openapi Navigator support?
It supports OpenAPI 3.x and Swagger 2.x specifications.
Can I load specs from a URL?
Yes, you can load specs from both local files and URLs.
Does the server handle multiple APIs at once?
Yes, it allows you to manage several API specifications simultaneously.
How does the search work?
The server uses fuzzy matching so you can search endpoints and schemas using natural language queries.
What does "reference preservation" mean?
The server maintains the $ref structures found in OpenAPI specs, keeping them intact for agent decision-making.