Into_-To_-MCP

# MCP Chat MCP Chat is a command-line interface application that enables interactive chat capabilities with local Ollama models. The application supports document retrieval, command-based prompts, and extensible tool integrations via the MCP (Model Control Protocol) architecture. ## Prerequisites - Python 3.10+ - [Ollama](https://ollama.com/) installed and running locally - A local model pulled in Ollama (for example `mistral`) ## Setup ### Step 1: Configure the environment variables 1. Create or edit the `.env` file in the project root and verify that the following variables are set correctly: ``` OLLAMA_MODEL="mistral" OLLAMA_BASE_URL="http://localhost:11434/v1" OLLAMA_API_KEY="ollama" # Any non-empty value works for local Ollama ``` ### Step 2: Install dependencies #### Option 1: Setup with uv (Recommended) [uv](https://github.com/astral-sh/uv) is a fast Python package installer and resolver. 1. Install uv, if not already installed: ```bash pip install uv ``` 2. Create and activate a virtual environment: ```bash uv venv source .venv/bin/activate # On Windows: .venv\Scripts\activate ``` 3. Install dependencies: ```bash uv pip install -e . ``` 4. Run the project ```bash uv run main.py ``` #### Option 2: Setup without uv 1. Create and activate a virtual environment: ```bash python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate ``` 2. Install dependencies: ```bash pip install openai python-dotenv prompt-toolkit "mcp[cli]==1.8.0" ``` 3. Run the project ```bash python main.py ``` ### Step 3: Ensure Ollama is ready ```bash ollama pull mistral ollama serve ``` ## Usage ### Basic Interaction Simply type your message and press Enter to chat with the model. ### Document Retrieval Use the @ symbol followed by a document ID to include document content in your query: ``` > Tell me about @deposition.md ``` ### Commands Use the / prefix to execute commands defined in the MCP server: ``` > /summarize deposition.md ``` Commands will auto-complete when you press Tab. ### Tools Available - `read_doc(doc_id)`: Read a document from the in-memory `docs` dictionary. - `edit_doc(doc_id, content)`: Edit or create a document in the in-memory `docs` dictionary. ## Development ### Adding New Documents Edit the `mcp_server.py` file to add new documents to the `docs` dictionary. ### Implementing MCP Features The core MCP features are implemented in: 1. `mcp_server.py` for tools, resources, and prompts 2. `mcp_client.py` for tool, prompt, and resource calls ### Linting and Typing Check There are no lint or type checks implemented.