Mew

Provides a starter MCP server with Bearer authentication and tools for job search and image processing.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "devreev-mew__mcp": {
      "command": "python",
      "args": [
        "mcp_starter.py"
      ],
      "env": {
        "MY_NUMBER": "YOUR_NUMBER_HERE",
        "AUTH_TOKEN": "YOUR_TOKEN_HERE"
      }
    }
  }
}

You can extend Puch AI with an MCP server that safely connects to external tools and data sources. This starter provides Bearer token authentication, a basic job search tool, and an image processing tool, all ready to run locally and exposed for use by your AI conversations.

How to use

You will run the MCP server locally and connect it from Puch AI to enable tool actions in conversations. Start the server, expose it if needed, and then link it in your Puch AI session using the connect command. The server provides two built-in tools: a Job Finder tool and an Image Processing tool. You will authenticate with a secret token and supply your phone number to enable secure interactions.

How to install

Prerequisites: make sure you have Python 3.11 or higher installed.

# Create virtual environment
uv venv

# Install all required packages
uv sync

# Activate the environment
source .venv/bin/activate

Additional steps and notes

Configure environment variables in a file named .env at the project root. Create the file by copying the example and then fill in your values.

# Copy the example file
cp .env.example .env

Edit .env to include your authentication token and your WhatsApp number in the format country code followed by the number.

AUTH_TOKEN=your_secret_token_here
MY_NUMBER=919876543210

Security and connectivity

The server uses Bearer token authentication for secure access. Keep your AUTH_TOKEN secret. To connect Puch AI to your MCP server, you will typically run the server locally and then expose it if needed for remote access.

If you need to make your local server accessible over the internet, you can expose it via a tunneling service. The setup shown here describes using a tunnel to publish the local port so Puch AI can reach your server securely.

Available tools

job_finder

Analyzes job descriptions, fetches postings from URLs, and searches for jobs using natural language to identify opportunities.

image_to_bw

Converts uploaded images to black and white for quick visual processing.