Sealmetrics MCP Server
Connects AI assistants like Claude to Sealmetrics analytics data, enabling natural language queries for traffic analysis, conversions, marketing performance, ROAS tracking, and funnel analysis.
README
Sealmetrics MCP Server
A Model Context Protocol (MCP) server that connects AI assistants like Claude to your Sealmetrics analytics data. Query traffic, conversions, and marketing performance using natural language.
Features
- Traffic Analysis: Query traffic by source, medium, campaign, or country
- Conversions: Get sales and conversion data with attribution
- Microconversions: Track add-to-cart, signups, and other engagement events
- Funnel Analysis: Analyze conversion funnel performance
- ROAS Evolution: Track return on ad spend over time
- Page Performance: Analyze page views and landing page effectiveness
- Pixel Generation: Generate tracking pixels for Google Tag Manager
Installation
Install the package using pipx (recommended) or pip:
# Using pipx (recommended - isolated environment)
brew install pipx # macOS
pipx install sealmetrics-mcp
# Or using pip
pip install sealmetrics-mcp
Claude Desktop Configuration
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Option A: Using pipx (Recommended)
If you installed with pipx, the executable is at ~/.local/bin/sealmetrics-mcp:
{
"mcpServers": {
"sealmetrics": {
"command": "/Users/YOUR_USERNAME/.local/bin/sealmetrics-mcp",
"args": [],
"env": {
"SEALMETRICS_API_TOKEN": "your-api-token-here",
"SEALMETRICS_ACCOUNT_ID": "your-account-id-here"
}
}
}
}
Note: Replace
YOUR_USERNAMEwith your actual username. You can find the path by runningwhich sealmetrics-mcpafter installation.
Option B: Using uvx
If you have uv installed (brew install uv):
{
"mcpServers": {
"sealmetrics": {
"command": "uvx",
"args": ["sealmetrics-mcp"],
"env": {
"SEALMETRICS_API_TOKEN": "your-api-token-here",
"SEALMETRICS_ACCOUNT_ID": "your-account-id-here"
}
}
}
}
Option C: Using Python directly
If the package is installed in a virtual environment or globally:
{
"mcpServers": {
"sealmetrics": {
"command": "python",
"args": ["-m", "sealmetrics_mcp"],
"env": {
"SEALMETRICS_API_TOKEN": "your-api-token-here",
"SEALMETRICS_ACCOUNT_ID": "your-account-id-here"
}
}
}
}
After Configuration
- Save the configuration file
- Restart Claude Desktop completely (Cmd+Q on macOS, then reopen)
- The Sealmetrics tools should appear in Claude's available tools
Troubleshooting
If the MCP server disconnects:
-
Verify the executable path exists:
ls -la ~/.local/bin/sealmetrics-mcp -
Test the server manually:
SEALMETRICS_API_TOKEN="your-token" ~/.local/bin/sealmetrics-mcpYou should see:
Starting Sealmetrics MCP server -
Check Claude Desktop logs:
# macOS cat ~/Library/Logs/Claude/mcp-server-sealmetrics.log -
Common issues:
- Path to executable is incorrect
- API token is invalid or expired
- Missing environment variables
- Claude Desktop not fully restarted
Environment Variables
| Variable | Required | Description |
|---|---|---|
SEALMETRICS_API_TOKEN |
Yes* | Your Sealmetrics API token (recommended) |
SEALMETRICS_ACCOUNT_ID |
No | Default account ID for queries |
SEALMETRICS_EMAIL |
Yes* | Email for login (alternative to token) |
SEALMETRICS_PASSWORD |
Yes* | Password for login (alternative to token) |
*Either SEALMETRICS_API_TOKEN or both SEALMETRICS_EMAIL and SEALMETRICS_PASSWORD are required.
Available Tools
| Tool | Description |
|---|---|
get_accounts |
List available Sealmetrics accounts |
get_traffic_data |
Traffic by source, medium, campaign |
get_conversions |
Sales and conversion data |
get_microconversions |
Add-to-cart, signups, etc. |
get_funnel_data |
Conversion funnel analysis |
get_roas_evolution |
ROAS over time |
get_pages_performance |
Page views and landing pages |
generate_conversion_pixel |
Generate tracking pixel code |
Example Queries
Once configured, you can ask Claude questions like:
- "How much traffic did we get from Google Ads yesterday?"
- "Show me conversions from organic search this month"
- "What's our ROAS evolution for the last 30 days?"
- "Which landing pages are performing best?"
- "Generate a conversion pixel for newsletter signups"
Getting Your API Token
- Log in to your Sealmetrics dashboard
- Go to Settings → API
- Generate a new API token
- Copy the token to your Claude Desktop configuration
Support
- Documentation: https://sealmetrics.com/docs
- Issues: https://github.com/sealmetrics/mcp-server/issues
- Email: support@sealmetrics.com
License
MIT License - see LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.