Provides a tool to send text prompts to configured n8n workflows and retrieve the results, enabling the AI to interact with automated external workflows.
Click on "Install 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 All-in-One ServerTurn this webinar transcript into a blog post"
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 All-in-One Server
This is a versatile MCP server that demonstrates multiple capabilities of the Model Context Protocol (MCP). It provides tools for calculation, external integrations (webhooks), resources for context, and prompt templates.
Capabilities
🧮 Tools
Functions that the AI can execute:
Calculator: Basic arithmetic operations (
add,subtract,multiply,divide).Webhook Integration:
send_to_webhook- Sends a text prompt to a configured n8n workflow and returns the response.
📚 Resources
Contextual data the AI can read:
support://playbook: A full Customer Support Playbook containing company overview, tone rules, product details, and standard operating procedures.
📝 Prompts
Templates to structure AI interactions:
webinar_to_blog: A structured prompt template to convert webinar transcripts into engaging blog posts.
Prerequisites
Python 3.10+
uv: A fast Python package installer and resolver.
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"macOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
Node.js & npm (optional, for the MCP Inspector)
Setup
Open your terminal in this directory (
calculator_server).Initialize the project (if you haven't already):
uv initAdd the required dependencies:
uv add "mcp[cli]" httpx
Running the Server
You can run the server directly using uv:
Note: This will use stdio for communication, so it will expect input from stdin and won't show much output in the console unless connected to an MCP client.
Testing with MCP Inspector
To test the server using the MCP Inspector (a web-based tool to interact with your server):
This will launch the inspector in your browser. You can:
Tools: Test the calculator and webhook tools.
Resources: View the content of
support://playbook.Prompts: Execute the
webinar_to_blogtemplate.
Integration with Claude Desktop
To use this server with Claude for Desktop:
Open your Claude Desktop configuration file:
Windows:
%APPDATA%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Add the server configuration. You can copy the content from
claude_desktop_config.jsonin this directory:{ "mcpServers": { "calculator": { "command": "uv", "args": [ "--directory", "C:\\Users\\Your_Name\\Desktop\\mcps\\calculator_server", "run", "server.py" ] } } }Important: Make sure the path in
--directorymatches the actual absolute path to yourcalculator_serverfolder.Restart Claude for Desktop.