tumf/grafana-loki-mcp

Overview

An MCP (Model Context Protocol) server that enables AI assistants to query Grafana Loki logs. It translates natural language requests into LogQL queries and returns results, allowing developers to interact with log data through AI tools.

Best for

Best for
Developers who want to query Loki logs via AI assistants for debugging and monitoring

Use cases

• Query application logs from an AI coding assistant during debugging
• Automate log analysis by integrating with MCP-compatible AI agents
• Monitor system behavior by asking natural language questions about Loki data

How to use

Install

pip install grafana-loki-mcp

Tools exposed

• query_loki
• format_loki_results

Example client config

{\n  "mcpServers": {\n    "loki": {\n      "command": "uvx",\n      "args": [\n        "grafana-loki-mcp",\n        "-u",\n        "GRAFANA_URL",\n        "-k",\n        "GRAFANA_API_KEY"\n      ]\n    }\n  }\n}

Notes

An MCP (Model Context Protocol) server that enables AI assistants to query Grafana Loki logs. It translates natural language requests into LogQL queries and returns results, allowing developers to interact with log data through AI tools.

26 stars on GitHub. Last updated 2026-01-05. Licensed MIT.

Use cases

• Query application logs from an AI coding assistant during debugging
• Automate log analysis by integrating with MCP-compatible AI agents
• Monitor system behavior by asking natural language questions about Loki data

Pros

• Lightweight Python implementation with minimal dependencies
• Follows the MCP standard for easy integration with AI tools
• Simple setup for developers already running Grafana Loki

Cons

• Small community (26 stars) means limited support and fewer examples
• Requires a running Grafana Loki instance to be useful
• Documentation may be sparse for advanced use cases

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.