mcp-coding

This repository is an experiment to explore the Model Context Protocol (MCP) and local LLM orchestration. It is intended for learning and prototyping, not as a production-ready product.

The project includes:

• an MCP HTTP server (server.ts) with filesystem tools (read_file, write_file, list_files, delete_file)
• a CLI agent (main.ts) that talks to the LLM and executes MCP tool calls when needed

Requirements (first-time setup)

If you just cloned this repository, install only:

• Node.js
• Ollama

This repository currently defaults to qwen3.6:latest in adapters/ollama.llm.ts. If you keep that default, run:

ollama pull qwen3.6:latest

Initialize the project

npm install

Run locally

Start MCP server (terminal 1):

npm run server

Server endpoint:

• http://localhost:8080/mcp

Start agent (terminal 2):

npm run start

In the interactive prompt, type your requests. To exit:

exit

Use MCP Inspector

1. Make sure the MCP server is running:

npm run server

1. In another terminal, start Inspector:

npm run inspector

1. In Inspector, connect to:

http://localhost:8080/mcp

You can then inspect available tools and test tool calls against the local MCP server.

Available scripts

• npm run build - build TypeScript
• npm test - run Jest tests
• npm run start - run the agent (client.ts)
• npm run start:watch - run the agent in watch mode
• npm run server - run MCP server (server.ts)
• npm run server:watch - run MCP server in watch mode
• npm run inspector - run MCP Inspector

How it works

1. You enter a prompt in the CLI client.
2. The agent sends messages to the LLM through Ollama.
3. If the LLM returns tool calls, the client invokes tools on the MCP server.
4. Tool results are sent back to the LLM to continue the loop.

Repository structure

.
├── main.ts
├── server.ts
├── adapters/
│   ├── index.ts
│   └── ollama.llm.ts
├── ports/
│   ├── index.ts
│   └── llm.port.ts
├── package.json
└── tsconfig.json

License

ISC