UpasanaGhosh/mcp-chat
A CLI-based AI chat application using the Anthropic API, with support for document retrieval, command-driven interactions, and extensible integrations through the Model Control Protocol (MCP).
Platform-specific configuration:
{
"mcpServers": {
"mcp-chat": {
"command": "npx",
"args": [
"-y",
"mcp-chat"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
MCP Chat is a command-line interface application that enables interactive chat capabilities with AI models through the Anthropic API. The application supports document retrieval, command-based prompts, and extensible tool integrations via the MCP (Model Control Protocol) architecture.
.env file in the project root and verify that the following variables are set correctly:ANTHROPIC_API_KEY="" # Enter your Anthropic API secret keyuv is a fast Python package installer and resolver.
pip install uvuv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activateuv pip install -e .uv run main.pypython -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activatepip install anthropic python-dotenv prompt-toolkit "mcp[cli]==1.8.0"python main.pySimply type your message and press Enter to chat with the model.
Use the @ symbol followed by a document ID to include document content in your query:
> Tell me about @deposition.mdUse the / prefix to execute commands defined in the MCP server:
> /summarize deposition.mdCommands will auto-complete when you press Tab.
Edit the mcp_server.py file to add new documents to the docs dictionary.
To fully implement the MCP featu
Loading reviews...