MCP Chat
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Chat chat with Claude about @architecture.md"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Chat
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 Context Protocol) architecture.
See ARCHITECTURE.md for diagrams of how main.py, mcp_client.py, mcp_server.py, and the core/ modules fit together.
Prerequisites
Python 3.10+
Anthropic API Key
Related MCP server: MCP Chat
Setup
Step 1: Configure the environment variables
Copy
.env.exampleto.envin the project root and fill in the values:
cp .env.example .envANTHROPIC_API_KEY="" # Your Anthropic API secret key
CLAUDE_MODEL="claude-sonnet-4-5" # Model id to chat with
USE_UV=1 # 1 to launch the MCP server via uv, 0 for plain pythonANTHROPIC_API_KEY and CLAUDE_MODEL are both required — the app exits at startup if either is empty.
Step 2: Install dependencies
Option 1: Setup with uv (Recommended)
uv is a fast Python package installer and resolver.
Install uv, if not already installed:
pip install uvCreate and activate a virtual environment:
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activateInstall dependencies:
uv pip install -e .Run the project
uv run main.pyOption 2: Setup without uv
Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activateInstall dependencies:
pip install anthropic python-dotenv prompt-toolkit "mcp[cli]==1.8.0"Run the project
python main.pyUsage
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.mdCommands
Use the / prefix to execute prompts defined in the MCP server. Each command takes a document id:
> /format deposition.mdCommands will auto-complete when you press Tab. mcp_server.py currently defines one prompt, format.
Development
Adding New Documents
Edit the mcp_server.py file to add new documents to the docs dictionary.
Adding New MCP Servers
Pass additional server scripts as arguments; each is launched as its own MCP client and its tools are merged into the tool set offered to the model:
uv run main.py path/to/other_server.pyLinting and Typing Check
There are no lint or type checks wired into CI. To lint locally:
uvx ruff check .Available Tools
2 toolsedit_documentA
Edit a document by replacing a string in the documents content with a new string
Inputs: doc_id (required), new_str (required), old_str (required).
read_doc_contentsA
Read the contents of a document and return it as a string.
Inputs: doc_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one reads document content, the other edits by replacing text. There is zero overlap or ambiguity between them.
Both tools follow a verb_noun pattern (read_doc_contents, edit_document), but the noun forms differ slightly ('doc_contents' vs 'document'). This minor inconsistency doesn't hinder readability.
With only two tools, the server feels thin for a document manipulation domain. While the narrow focus is defensible, the count is below the typical 3-15 range and borders on insufficient.
The server provides read and edit (replace) operations, but lacks create, delete, list, or other common document lifecycle operations. These gaps could be worked around but represent notable missing functionality.
Related MCP Connectors
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA command-line interface application for interactive chat with AI models via the Anthropic API. It supports document retrieval, command-based prompts, and extensible tool integrations through the MCP architecture.-
- FlicenseAqualityDmaintenanceA command-line interface application enabling interactive chat with AI models via the Anthropic API. It supports document retrieval, command-based prompts, and extensible tool integrations through the MCP architecture.2-
- FlicenseNot gradedqualityDmaintenanceA command-line interface application that enables interactive chat with AI models via the Anthropic API, supporting document retrieval and command-based prompts through the MCP architecture.-
- FlicenseNot gradedqualityDmaintenanceA CLI chat application enabling interactive conversations with AI models via the Anthropic API, with document retrieval and command-based prompt support through the MCP architecture.-