whitejoce/hot-update-MCP-Server
3.1
If you are the rightful owner of hot-update-MCP-Server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
This is a hot update server example based on the FastMCP framework, allowing dynamic loading and updating of utility functions without restarting the server.
MCP Hot Update Server Demo
| DeepWiki for this Repository
This is a hot update server example based on the FastMCP framework, allowing dynamic loading and updating of utility functions without restarting the server.
Features
- Supports dynamic loading of utility functions
- Manage tools via JSON configuration files
- Real-time hot update capability
- Detailed error handling and logging
Key Code
exec(tool_code, globals(), local_namespace)
if inspect.isfunction(obj) and obj.__name__ in local_namespace:
if found_func is not None:
# Handle potential duplicate function definition if needed
pass # Or log a warning, raise an error, etc.
found_func = obj
if found_func:
# Add the tool to MCP using the database name
mcp.tool(
name=tool_name, description=tool_description
)(found_func)
print(f"Successfully registered tool '{tool_name}'")
🚀 Quick Start
1️⃣ Environment Setup
Make sure you have Python 3.7+ installed. Then, install the required library:
$ pip install fastmcp
fastmcp: Python implementation library for MCP.
2️⃣ Run MCP Server
$ python server.py
- The
tools.jsonfile format is as follows:
[
{
"name": "Tool Name",
"description": "Tool Description",
"code": "def function_name(params):\n # Function implementation\n return result"
}
]
Security Notes
⚠️ Important Security Warning:
- The current implementation uses
exec()to execute code read from the JSON file - Additional security measures are required for production environments:
- Code signature verification
- Sandbox environment restrictions
- Code review mechanisms
- Access control
Development Suggestions
- Test all utility functions in the development environment
- Ensure the JSON file format is correct
- Add appropriate error handling
- Implement a code review process
- Consider adding version control mechanisms
Workflow
graph TD
A[Start Server] --> B[Load tools.json]
B --> C{Parse JSON}
C -->|Success| D[Iterate Tool List]
C -->|Failure| E[Output Error Log]
D --> F[Execute Tool Code]
F --> G{Code Execution}
G -->|Success| H[Register to MCP]
G -->|Failure| I[Output Error Log]
H --> J[Server Running]
J --> K[Wait for New Requests]
