home / mcp / parallel poke mcp server

Parallel Poke MCP Server

Provides an MCP bridge between Parallel monitors and Poke for SMS alerts and monitor management.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "konarkm-parallel-poke-mcp": {
      "url": "https://your-app-url.com/mcp",
      "headers": {
        "POKE_API_KEY": "YOUR_POKE_API_KEY",
        "MCP_AUTH_TOKEN": "OPTIONAL_TOKEN",
        "PARALLEL_API_KEY": "YOUR_PARALLEL_API_KEY",
        "WEBHOOK_BASE_URL": "https://your-app-url.com",
        "PARALLEL_WEBHOOK_SECRET": "OPTIONAL_SECRET",
        "NOTIFY_COMPLETION_EVENTS": "true|false"
      }
    }
  }
}

You can bridge Parallel monitors with Poke to receive SMS alerts when changes occur and to manage monitors via chat. This MCP server listens for webhooks from Parallel, forwards details to Poke for notifications, and exposes tools to create, update, and list monitors from your conversations.

How to use

You connect a Poke client to this MCP server to manage your Parallel monitors and receive SMS updates. Start by deploying the server and linking it to your Poke account. Then you can text Poke to create monitors, list your monitors, view recent events, or delete a monitor. When a monitor detects changes, the server forwards the event data to Poke, which formats an SMS and sends it to you. You can also let Poke call the MCP tools to create, update, or delete monitors directly.

Key capabilities you can use from Poke include creating a monitor with a cadence, listing all monitors, retrieving details for a specific monitor, updating a monitor’s cadence or webhook, deleting a monitor, and fetching recent events across monitors.

How to install

Prerequisites you need on your machine or hosting environment:

- Python 3.8+ (for the MCP server)

- Access to a hosting platform or a local environment to run the Python service

Follow these steps to deploy and run the server locally as a development setup:

# 1. Clone the repository
git clone https://github.com/konarkm/parallel-poke-mcp.git
cd parallel-poke-mcp

# 2. Create a virtual environment
python3 -m venv venv
source venv/bin/activate  # use venv\Scripts\activate on Windows

# 3. Install dependencies
pip install -r requirements.txt

# 4. Set up environment variables
# Copy example and edit with your actual keys
cp .env.example .env
# Edit .env with your API keys and settings

# 5. Run the server
python3 src/server.py
```

Test tooling (optional):

```bash
npx @modelcontextprotocol/inspector
```

Connect to the server at http://localhost:8000/mcp using the MCP Inspector to verify the endpoint.

Additional sections

Configuration, security, usage examples, troubleshooting, and notes are described below to help you operate smoothly.

Available tools

create_monitor

Create a new monitor with a query and cadence (hourly/daily/weekly)

list_monitors

List all your active monitors

get_monitor

Get details of a specific monitor

update_monitor

Update a monitor (cadence, webhook, metadata)

delete_monitor

Delete a monitor

list_recent_events

Get recent events across monitors