Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@fastapi-mcp-inspect show all routes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mount an MCP server onto your FastAPI application to let AI agents inspect your routes, endpoints, and schemas at runtime.
uv add fastapi-mcp-inspect
# or using pip: pip install fastapi-mcp-inspectRelated MCP server: FastAPI-MCP
from fastapi import FastAPI
from fastapi_mcp_inspect import FastAPIInspect
app = FastAPI()
FastAPIInspect(app, mount_path="/mcp")Any LLM with MCP support can now connect to your app's /mcp endpoint and
inspect all registered routes.
show_all_routes()Lists every registered route with its HTTP methods, summary, description, and total count.
show_endpoint_details(method, endpoint)Shows detailed information for a specific endpoint, including request/response schemas and any referenced Pydantic models.
search_routes(query, method=None, search_in_summary=False, tags=None)Searches routes by path (case-insensitive) with optional filters:
method — filter by HTTP method (e.g. GET, POST).
search_in_summary — when True, also matches against summaries and descriptions.
tags — filter by tag names (OR logic — any match).
list_all_tags()Lists every unique tag used across API routes with route counts.
get_schema_definition(schema_name)Returns the full field-level definition of a Pydantic schema used by any endpoint. Lookup is case-insensitive.
git clone https://github.com/inclinedadarsh/fastapi-mcp-inspect.git
cd fastapi-mcp-inspect
uv syncMIT
This server cannot be deployed
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
