MCP Dump

A collection of MCP servers, clients, and experiments for learning, prototyping, and comparing runtimes across environments.

other

0

GitHub Stars

other

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "jayanth-mkv-mcp-dump": {
      "command": "uv",
      "args": [
        "run",
        "mcp-server"
      ],
      "env": {
        "UV_RUN": "uv run mcp-server"
      }
    }
  }
}

MCP enables structured exchanges between tools, agents, and large language models so you can build richer, multi-step workflows with clear inputs, outputs, and state. This server lets you run an MCP workspace locally in Python with uvx-style execution and explore a lightweight Cloudflare Workers example as well.

How to use

Start the Python MCP server locally using the uv runner, then try a sample client to see how MCP can coordinate a reactive agent. For edge deployments, you can also run a minimal Cloudflare Workers MCP server to observe deployment and testing patterns in an edge environment.

How you typically use MCP in this setup:

How to install

# Prerequisites
- Node.js and npm
- Python (for the Python MCP workspace)
- uv tool (for Python MCP server execution)
- Cloudflare Wrangler (optional, for edge deployment)

Install and run the Cloudflare Workers MCP server example (mcp-hello)

cd mcp-hello
npm install
npm test
npx wrangler dev

Install and run the Python MCP workspace (mcp-files)

cd mcp-files
uv run mcp-server

Try a client example from the Python workspace to exercise a reactive agent pattern

uv run examples/clients/react_agent.py

Additional notes

Explore available tools and endpoints by invoking help on the server: uv run mcp-server --help.

uv run mcp-server --help