Merge pull request #110 from shira-ayal/mintlify-docs

Mintlify docs

Author: Shira Ayal

README.md

@@ -11,6 +11,7 @@
 
 </div>
 
+
 <p align="center"><a href="https://github.com/tadata-org/fastapi_mcp"><img src="https://github.com/user-attachments/assets/b205adc6-28c0-4e3c-a68b-9c1a80eb7d0c" alt="fastapi-mcp-usage" height="400"/></a></p>
 
 
@@ -65,15 +66,7 @@ That's it! Your auto-generated MCP server is now available at `https://app.base.
 
 ## Documentation, Examples and Advanced Usage
 
-FastAPI-MCP provides comprehensive documentation in the `docs` folder:
-- [Best Practices](docs/00_BEST_PRACTICES.md) - Essential guidelines for converting APIs to MCP tools safely and effectively
-- [FAQ](docs/00_FAQ.md) - Frequently asked questions about usage, development and support
-- [Tool Naming](docs/01_tool_naming.md) - Best practices for naming your MCP tools using operation IDs
-- [Connecting to MCP Server](docs/02_connecting_to_the_mcp_server.md) - How to connect various MCP clients like Cursor and Claude Desktop
-- [Authentication and Authorization](docs/03_authentication_and_authorization.md) - How to authenticate and authorize your MCP tools
-- [Advanced Usage](docs/04_advanced_usage.md) - Advanced features like custom schemas, endpoint filtering, and separate deployment
-
-Check out the [examples directory](examples) for code samples demonstrating these features in action.
+FastAPI-MCP provides [comprehensive documentation](https://fastapi-mcp.tadata.com/). Additionaly, check out the [examples directory](examples) for code samples demonstrating these features in action.
 
 ## FastAPI-first Approach
 
@@ -83,7 +76,7 @@ FastAPI-MCP is designed as a native extension of FastAPI, not just a converter t
 
 - **ASGI transport**: Communicates directly with your FastAPI app using its ASGI interface, eliminating the need for HTTP calls from the MCP to your API
 
-- **Unified infrastructure**: Your FastAPI app doesn't need to run separately from the MCP server (though [separate deployment](docs/04_advanced_usage.md#deploying-separately-from-original-fastapi-app) is also supported)
+- **Unified infrastructure**: Your FastAPI app doesn't need to run separately from the MCP server (though [separate deployment](https://fastapi-mcp.tadata.com/advanced/deploy#deploying-separately-from-original-fastapi-app) is also supported)
 
 This design philosophy ensures minimum friction when adding MCP capabilities to your existing FastAPI services.
 

docs/02_connecting_to_the_mcp_server.md

@@ -1,4 +1,7 @@
-# Authentication and Authorization
+---
+title: Authentication & Authorization
+icon: key
+---
 
 FastAPI-MCP supports authentication and authorization using your existing FastAPI dependencies.
 
@@ -12,7 +15,7 @@ If you just want to be able to pass a valid authorization header, without suppor
 
 You just need to make sure your MCP client is sending it:
 
-```json
+```json {8-9, 13}
 {
   "mcpServers": {
     "remote-example": {
@@ -35,7 +38,7 @@ This is enough to pass the authorization header to your FastAPI endpoints.
 
 Optionally, if you want your MCP server to reject requests without an authorization header, you can add a dependency:
 
-```python
+```python {1-2, 7-9}
 from fastapi import Depends
 from fastapi_mcp import FastApiMCP, AuthConfig
 
@@ -49,15 +52,15 @@ mcp = FastApiMCP(
 mcp.mount()
 ```
 
-For a complete working example of authorization header, check out the [auth_example_token_passthrough.py](/examples/08_auth_example_token_passthrough.py) in the examples folder.
+For a complete working example of authorization header, check out the [Token Passthrough Example](https://github.com/tadata-org/fastapi_mcp/blob/main/examples/08_auth_example_token_passthrough.py) in the examples folder.
 
 ## OAuth Flow
 
 FastAPI-MCP supports the full OAuth 2 flow, compliant with [MCP Spec 2025-03-26](https://modelcontextprotocol.io/specification/2025-03-26/basic/authorization).
 
 It would look something like this:
 
-```python
+```python {7-16}
 from fastapi import Depends
 from fastapi_mcp import FastApiMCP, AuthConfig
 
@@ -102,7 +105,7 @@ You can use it with any OAuth provider that supports the OAuth 2 spec. See expla
 
 If you already have a properly configured OAuth server that works with MCP clients, or if you want full control over the metadata, you can provide your own OAuth metadata directly:
 
-```python
+```python {9, 22}
 from fastapi import Depends
 from fastapi_mcp import FastApiMCP, AuthConfig
 
@@ -140,7 +143,7 @@ For this to work, you have to make sure mcp-remote is running [on a fixed port](
 
 ## Working Example with Auth0
 
-For a complete working example of OAuth integration with Auth0, check out the [auth_example_auth0.py](/examples/09_auth_example_auth0.py) in the examples folder. This example demonstrates the simple case of using Auth0 as an OAuth provider, with a working example of the OAuth flow.
+For a complete working example of OAuth integration with Auth0, check out the [Auth0 Example](https://github.com/tadata-org/fastapi_mcp/blob/main/examples/09_auth_example_auth0.py) in the examples folder. This example demonstrates the simple case of using Auth0 as an OAuth provider, with a working example of the OAuth flow.
 
 For it to work, you need an .env file in the root of the project with the following variables:
 
@@ -221,5 +224,4 @@ Proxies solve several problems:
 
 Normally, mcp-remote will start on a random port, making it impossible to configure the OAuth provider's callback URL properly.
 
-
-You have to make sure mcp-remote is running on a fixed port, for example `8080`, and then configure the callback URL to `http://127.0.0.1:8080/oauth/callback` in your OAuth provider.
+You have to make sure mcp-remote is running on a fixed port, for example `8080`, and then configure the callback URL to `http://127.0.0.1:8080/oauth/callback` in your OAuth provider.

docs/04_advanced_usage.md

@@ -0,0 +1,35 @@
+---
+title: Deploying the Server
+icon: play
+---
+
+## Deploying separately from original FastAPI app
+
+You are not limited to serving the MCP on the same FastAPI app from which it was created.
+
+You can create an MCP server from one FastAPI app, and mount it to a different app:
+
+```python {9, 15, }
+from fastapi import FastAPI
+from fastapi_mcp import FastApiMCP
+
+# Your API app
+api_app = FastAPI()
+# ... define your API endpoints on api_app ...
+
+# A separate app for the MCP server
+mcp_app = FastAPI()
+
+# Create MCP server from the API app
+mcp = FastApiMCP(api_app)
+
+# Mount the MCP server to the separate app
+mcp.mount(mcp_app)
+```
+
+Then, you can run both apps separately:
+
+```bash
+uvicorn main:api_app --host api-host --port 8001
+uvicorn main:mcp_app --host mcp-host --port 8000
+```

docs/03_authentication_and_authorization.md renamed to docs/advanced/auth.mdx

@@ -0,0 +1,25 @@
+---
+title: Refreshing the Server
+description: Adding endpoints after MCP server creation
+icon: arrows-rotate
+---
+
+If you add endpoints to your FastAPI app after creating the MCP server, you'll need to refresh the server to include them:
+
+```python {9-12, 15}
+from fastapi import FastAPI
+from fastapi_mcp import FastApiMCP
+
+app = FastAPI()
+
+mcp = FastApiMCP(app)
+mcp.mount()
+
+# Add new endpoints after MCP server creation
+@app.get("/new/endpoint/", operation_id="new_endpoint")
+async def new_endpoint():
+    return {"message": "Hello, world!"}
+
+# Refresh the MCP server to include the new endpoint
+mcp.setup_server()
+```

docs/advanced/deploy.mdx

@@ -0,0 +1,31 @@
+---
+title: Transport
+description: How to communicate with the FastAPI app
+icon: car
+---
+
+FastAPI-MCP uses ASGI transport by default, which means it communicates directly with your FastAPI app without making HTTP requests. This is more efficient and doesn't require a base URL.
+
+It's not even necessary that the FastAPI server will run.
+
+If you need to specify a custom base URL or use a different transport method, you can provide your own `httpx.AsyncClient`:
+
+```python {7-10, 14}
+import httpx
+from fastapi import FastAPI
+from fastapi_mcp import FastApiMCP
+
+app = FastAPI()
+
+custom_client = httpx.AsyncClient(
+    base_url="https://api.example.com",
+    timeout=30.0
+)
+
+mcp = FastApiMCP(
+    app,
+    http_client=custom_client
+)
+
+mcp.mount()
+```