CustomMCPServer
About
build a custom MCP server in Python and connect that to an AI agent.
Details
- Author
- abhimvp
- Downloads
- 132
- Categories
- Other
Jump to
- Expose data through Resources (load information into LLM context)
- Provide functionality through Tools (execute code or produce side effects)
- Define interaction patterns through Prompts (reusable LLM templates)
- Built on the Python MCP Server SDK
- Can be installed directly into Claude Desktop
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
CustomMCPServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Start by creating a uv‑managed project with uv init ., then add the MCP CLI dependency with uv add "mcp[cli]". Activate the virtual environment, run uv run mcp install main.py to install the server in Claude Desktop, and restart the Claude app to see the server appear. For an advanced server, add black and then run uv run mcp install adv_main.py.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"custommcpserver": {
"CustomMCPServer": {
"command": "uv",
"args": [
"init",
"."
]
}
}
}
}McpServers
{
"CustomMCPServer": {
"command": "uv",
"args": [
"init",
"."
]
}
}CustomMCPServer
Build a custom MCP server in Python and connect that to an AI agent.
- Resources:
- Python MCP Server SDK
- Reference Code
- MCP servers are essentially how LLM and AI Tools communicate with each other.The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction.
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
