Spaces:
Running
Running
Merge pull request #3 from jlowin/readme
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
|
| 5 |
A fast, pythonic way to build Model Context Protocol (MCP) servers.
|
| 6 |
|
| 7 |
-
|
| 8 |
|
| 9 |
## Installation
|
| 10 |
|
|
@@ -115,15 +115,3 @@ fastmcp install your_server.py --with-editable . --with pandas --with numpy
|
|
| 115 |
```
|
| 116 |
|
| 117 |
|
| 118 |
-
## Configuration
|
| 119 |
-
|
| 120 |
-
FastMCP can be configured via environment variables with the prefix `FASTMCP_`:
|
| 121 |
-
|
| 122 |
-
- `FASTMCP_DEBUG`: Enable debug mode
|
| 123 |
-
- `FASTMCP_LOG_LEVEL`: Set logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
|
| 124 |
-
- `FASTMCP_HOST`: HTTP server host (default: 0.0.0.0)
|
| 125 |
-
- `FASTMCP_PORT`: HTTP server port (default: 8000)
|
| 126 |
-
|
| 127 |
-
## License
|
| 128 |
-
|
| 129 |
-
Apache 2.0
|
|
|
|
| 4 |
|
| 5 |
A fast, pythonic way to build Model Context Protocol (MCP) servers.
|
| 6 |
|
| 7 |
+
Anthropic's new [Model Context Protocol](https://modelcontextprotocol.io) is powerful way to give broadcast new functionality and context to LLMs. However, developing MCP servers can be cumbersome. FastMCP provides a simple, intuitive interface for creating MCP servers in Python.
|
| 8 |
|
| 9 |
## Installation
|
| 10 |
|
|
|
|
| 115 |
```
|
| 116 |
|
| 117 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|