MCP Tekmetric

by patclarke

141 downloads
Not rated
GitHub

About

MCP Tekmetric is a Model Context Protocol (MCP) server that enables AI assistants to interact with Tekmetric data in a read-only manner. It is designed for users who want to automate or retrieve information from their Tekmetric instance through an AI interface.

Details

Author
patclarke
Downloads
141
Categories
Other

- Read-only access to Tekmetric data
- Local Python or Docker deployment
- SSE transport for MCP connections
- Health check endpoint (/healthz)

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP Tekmetric
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Obtain a Tekmetric API key and set it as the TEKMETRIC_API_KEY environment variable. Run the server locally with uvicorn mcp_tekmetric.servers.main:asgi_app --host 0.0.0.0 --port 8080 or via Docker using docker run -e TEKMETRIC_API_KEY=your_key -p 8080:8080 mcp-tekmetric. Connect your AI assistant (e.g., VS Code Copilot) by configuring an SSE server at http://localhost:8080/sse.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp tekmetric": {
            "mcp-tekmetric": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-tekmetric",
                    "."
                ]
            }
        }
    }
}

McpServers

{
    "mcp-tekmetric": {
        "command": "docker",
        "args": [
            "build",
            "-t",
            "mcp-tekmetric",
            "."
        ]
    }
}

MCP Tekmetric

A Model Context Protocol (MCP) server designed to integrate AI assistants with Tekmetric. This project allows AI tools to interact with your Tekmetric data, enabling automation and intelligent workflows directly from your AI assistant.

Currently, this integration supports read-only actions, allowing your AI to retrieve information from your Tekmetric instance.

Example Usage

Leverage your AI assistant to interact with your Tekmetric data:

- 📅 Check Appointment Details: "What are the details for the appointment scheduled for tomorrow?"
- 🚗 Retrieve Shop Information: "Find the contact information of a Shop."
- 📊 Get Repair Order Status: "What is the current status of repair order #12345?"

image

---

🔐 Authentication Setup

You need a Tekmetric API key to authenticate with the Tekmetric API. Obtain your API key from your Tekmetric account settings.

Set your API key as a system environment variable:

export TEKMETRIC_API_KEY="your_tekmetric_api_key"

---

🚀 Quick Start Guide

Option 1: Run Locally (Python)

1. Clone this repository:

    git clone https://github.com/patclarke/mcp-tekmetric.git
    cd mcp-tekmetric
    

2. Install dependencies:

    pip install -e .
    

3. Start the server:

    uvicorn mcp_tekmetric.servers.main:asgi_app --host 0.0.0.0 --port 8080
    

---

Option 2: Run with Docker

1. Clone this repository:

    git clone https://github.com/patclarke/mcp-tekmetric.git
    cd mcp-tekmetric
    

2. Build the Docker image:

    docker build -t mcp-tekmetric .
    

3. Run the container (pass your Tekmetric API key):

    docker run -e TEKMETRIC_API_KEY=your_tekmetric_api_key -p 8080:8080 mcp-tekmetric
    

This will expose the server on http://localhost:8080.

---

🤖 Connect Your AI Assistant

For VS Code Copilot or another AI assistant that supports MCP:

Example .mcp.json config:

{
  "servers": {
    "local-tekmetric": {
      "type": "sse",
      "url": "http://localhost:8080/sse"
    }
  }
}

---

🧪 Health Check

To verify the server is running:

curl http://localhost:8080/healthz

You should see:

{"status": "ok"}

---

📄 License

MIT License

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.