Mezmo

Mezmo is an MCP server that retrieves logs directly from the Mezmo observability platform into Model Context Protocol environments. Designed for developers, site reliability engineers, and system administrators, it connects AI development interfaces with cloud log streams to streamline incident triage and debugging. Users can query real-time and historical application logs without leaving their primary coding workflow. The server includes quota-conscious design choices and intelligent defaults, automatically pulling from a six-hour window and limiting output to ten logs unless adjusted. Through the get_logs tool, developers can isolate logs across selected applications, filter by specific severity levels like ERROR and WARNING, and execute string-based queries. By handling retries, time ranges, and authentication locally via Docker, it prevents unnecessary API quota consumption while letting users inspect error traces, investigate runtime crashes, and verify recent software deployments straight from compatible MCP assistants.

Category: Monitoring & Observability

Tags: logging, logs, mezmo, monitoring

Visit Mezmo

How to install and configure Mezmo

1. Obtain your Mezmo Service API key from your Mezmo dashboard. 2. Clone the repository and move into the project directory: bash git clone https://github.com/riefer02/mezmo-logs-mcp cd mezmo-logs-mcp 3. Copy the sample environment file and add your credentials: bash cp env.example .env Set MEZMO_API_KEY inside .env. 4. Build and start the container: bash docker-compose up -d 5. For Cursor, add the server to .cursor/mcp.json: json { "mcpServers": { "mezmo": { "url": "http://localhost:18080/mcp", "transport": "streamable-http", "description": "Mezmo log retrieval" } } } For Claude Desktop, add to your MCP settings: json { "mcpServers": { "mezmo": { "command": "docker", "args": ["exec", "mezmo-mcp-server", "python", "server.py"] } } } 6. Restart your MCP client.

What you can do with Mezmo

• Inspect recent error traces by filtering application log streams for ERROR and WARNING severity levels directly from your client. * Discover running services and log structures using low-count log retrieval before scaling up diagnostic queries. * Search application runtime output for specific keywords, such as database connection drops or unhandled exceptions. * Pull historical log records within custom timestamp boundaries to audit specific production incidents without opening web dashboards.

Key facts

• https://github.com/riefer02/mezmo-logs-mcp
• Monitoring & Observability
• logging, logs, mezmo, monitoring

Part of MCP Servers

How do I install Mezmo MCP server?

You install the server by cloning its GitHub repository, creating a local .env configuration containing your MEZMO_API_KEY, and running docker-compose up -d. Afterwards, add the connection configuration to your preferred MCP client such as Cursor or Claude Desktop and restart the application.

What can Mezmo MCP server do?

It provides the get_logs tool to fetch logs from the Mezmo platform. It allows users to filter log events by specific application names, restrict queries by severity levels, search specific strings, and define custom time intervals using Unix timestamps.

Which MCP clients work with Mezmo?

Mezmo supports any client compatible with the Model Context Protocol. Documented setups include Cursor using streamable-http over port 18080 and Claude Desktop using docker exec commands to run the Python server process.

How does the server manage API quotas?

The server applies sensible defaults, fetching only 10 logs across the preceding six hours when parameters are omitted. Users are encouraged to first inspect a small sample, filter by specific app and severity, and then increase the record count.