Quickchat AI MCP Server

What is Quickchat AI MCP Server about?

The Quickchat AI MCP Server acts as a bridge between Quickchat AI agents and any AI application that supports the Model Context Protocol. By running a small Python‑based server, developers can expose their custom Quickchat agents as MCP services, allowing tools such as Claude Desktop, Cursor, VS Code extensions, and other MCP‑compatible clients to invoke the agent directly.

How to use Quickchat AI MCP Server?

1. Create a Quickchat AI account and start a trial or paid plan.
2. Configure your agent – set up the knowledge base, capabilities, and any custom settings in the Quickchat dashboard.
3. Activate the MCP on the Quickchat MCP page, providing a name, description, and optional command.
4. Install the uv package manager:

   curl -LsSf https://astral.sh/uv/install.sh | sh
   

5. Add a server entry to the client’s MCP configuration (e.g., Claude Desktop or Cursor) using the snippet provided in the README, filling in SCENARIO_ID and API_KEY.
6. Run the server – the default command uvx quickchat-ai-mcp starts the MCP service.
7. Test the integration by issuing a request from the AI client; the conversation will appear in the Quickchat inbox.

Key features of Quickchat AI MCP Server

• Dynamic configuration – change name, description, or agent settings from the Quickchat dashboard with a single click.
• Full‑duplex conversation logging – all interactions are stored in the Quickchat inbox for review.
• Multi‑client support – works with Claude Desktop, Cursor, VS Code, Windsurf, and any future MCP‑compatible application.
• Secure optional authentication – you can require or hide the API key for end‑users.
• Debug tools – built‑in support for the MCP inspector and easy local debugging via uv run commands.

Use cases of Quickchat AI MCP Server

• Embedding a specialized knowledge base into developer tools (e.g., code assistance in VS Code).
• Customer‑support bots accessible from chat‑oriented AI assistants.
• Prototyping AI‑enhanced workflows where rapid iteration of agent behavior is needed.
• Providing AI‑powered features in internal tools without exposing your API key to end users.

FAQ from the Quickchat AI MCP Server

Q: Do I need to expose my Quickchat API key to users? A: No. Turn the Require API key toggle off on the MCP page and share a configuration snippet that only contains SCENARIO_ID.

Q: Which package manager should I use? A: The project recommends uv for installation and execution, but any Python environment capable of running the quickchat-ai-mcp package will work.

Q: Can I run the server in production? A: Yes. Deploy the same command (uvx quickchat-ai-mcp) on a server or container; the Quickchat dashboard handles updates to the agent logic.

Q: How do I debug issues? A: Use the MCP inspector (uv run mcp dev src/__main__.py) or run the server with the debug command shown in the README.

Q: What clients are supported? A: Any client that implements the Model Context Protocol, including Claude Desktop, Cursor, VS Code extensions, Windsurf, and future integrations listed on the MCP feature‑support matrix.

Quickchat AI MCP server

The Quickchat AI MCP (Model Context Protocol) server allows you to let anyone plug in your Quickchat AI Agent into their favourite AI app such as Claude Desktop, Cursor, VS Code, Windsurf and more.

Quickstart

1. Create a Quickchat AI account and start a 7-day trial of any plan.
2. Set up your AI's Knowledge Base, capabilities and settings.
3. Go to the MCP page to activate your MCP. Give it Name, Description and (optional) Command. They are important - AI apps need to understand when to contact your AI, what its capabilities and knowledge are.
4. That's it! Now you're ready to test your Quickchat AI via any AI app and show it to the world!

Useful links

• Quickstart video youtube.com/watch?v=JE3dNiyZO8w
• Quickstart blog post: quickchat.ai/post/how-to-launch-your-quickchat-ai-mcp
• MCP (Model Context Protocol) explained: quickchat.ai/post/mcp-explained
• The Quickchat AI MCP package on PyPI: pypi.org/project/quickchat-ai-mcp
• The Quickchat AI MCP GitHub repo: github.com/quickchatai/quickchat-ai-mcp

Prerequisite

Install uv using:

curl -LsSf https://astral.sh/uv/install.sh | sh

or read more here.

Test with Claude Desktop

Configuration

Go to Settings > Developer > Edit Config. Open the claude_desktop_config.json file in a text editor. If you're just starting out, the file is going to look like this:

{
  "mcpServers": {}
}

This is where you can define all the MCPs your Claude Desktop has access to. Here is how you add your Quickchat AI MCP:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP NAME >": {
      "command": "uvx",
      "args": ["quickchat-ai-mcp"],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI SCENARIO ID >",
        "API_KEY": "< QUICKCHAT AI API KEY >"
      }
    }
  }
}

Go to the Quickchat AI app > MCP > Integration to find the above snippet with the values of MCP Name, SCENARIO_ID and API_KEY filled out.

Test with Cursor

Configuration

Go to Settings > Cursor Settings > MCP > Add new global MCP server and include the Quickchat AI MCP snippet:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP NAME >": {
      "command": "uvx",
      "args": ["quickchat-ai-mcp"],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI SCENARIO ID >",
        "API_KEY": "< QUICKCHAT AI API KEY >"
      }
    }
  }
}

As before, you can find values for MCP Name, SCENARIO_ID and API_KEY at Quickchat AI app > MCP > Integration.

Test with other AI apps

Other AI apps will most likely require the same configuration but the actual steps to include it in the App itself will be different. We will be expanding this README as we go along.

Launch your Quickchat AI MCP to the world!

⛔️ Do not publish your Quickchat API key to your users!

Once you're ready to let other users connect your Quickchat AI MCP to their AI apps, share configuration snippet with them! However, you need to make sure they can use your Quickchat AI MCP without your Quickchat API key. Here is how to do that:

1. On the Quickchat App MCP page, turn the Require API key toggle OFF.
2. Share the configuration snippet without the API key:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP NAME >": {
      "command": "uvx",
      "args": ["quickchat-ai-mcp"],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI SCENARIO ID >"
      }
    }
  }
}

---

Cool features

• You can control all aspects of your MCP from the Quickchat AI dashboard. One click and your change is deployed. That includes the MCP name and description - all your users need to do is refresh their MCP connection.
• View all conversations in the Quickchat Inbox. Remember: those won't be the exact messages your users send to their AI app but rather the transcript of the AI <> AI interaction between their AI app and your Quickchat AI. 🤯
• Unlike most MCP implementations, this isn't a static tool handed to an AI. It's an open-ended way to send messages to Quickchat AI Agents you create. 🙌

---

Running from source

Debugging with the MCP inspector

uv run mcp dev src/__main__.py

Debugging with Claude Desktop, Cursor or other AI apps

Use the following JSON configuration:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP NAME >": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with",
        "requests",
        "mcp",
        "run",
        "< YOUR PATH>/quickchat-ai-mcp/src/__main__.py"
      ],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI SCENARIO ID >",
        "API_KEY": "< QUICKCHAT AI API KEY >"
      }
    }
  }
}

Testing

Make sure your code is properly formatted and all tests are passing:

ruff check --fix
ruff format
uv run pytest

GitHub Star History