MCPs
Grafana-Loki MCP Server

Grafana-Loki MCP Server

A FastMCP server for querying Grafana Loki logs via the Model Context Protocol.

Stars

Forks

Watchers

Issues

Grafana-Loki MCP Server is a FastMCP-compliant server that enables querying and formatting of Grafana Loki logs using the Model Context Protocol (MCP). It supports various transport protocols (stdio and SSE) and provides tools for querying logs, retrieving labels and label values, and formatting log results in multiple output formats. The server integrates with Grafana's API, offering both command-line and environment variable configuration options for flexibility. Designed for seamless integration into AI model context workflows, it enhances log retrieval and processing in context-aware applications.

Key Features

MCP-compliant server for Grafana Loki

Query Loki logs via Grafana API

Support for stdio and SSE transport protocols

Flexible output formatting (text, JSON, markdown)

Retrieve Loki labels and label values

Configuration via environment variables or CLI arguments

Integration with FastMCP ecosystem

Max per line log processing option

Development and testing utilities

Support for Python 3.10+ installation

Use Cases

Automating log queries for Grafana Loki through context-aware platforms

Integrating Loki log data into AI model workflows via MCP

Retrieving and formatting logs for analysis in operational scripts

Fetching label names and label values from Loki for dynamic monitoring

Providing log insights to AI assistants through MCP tools

Streamlining backend diagnostics with automated log retrieval

Facilitating observability data access for AI-powered systems

Batch processing of log data with controlled output formatting

Enhancing DevOps workflows with standardized log querying

Programmatically embedding log information in context-driven applications

README

Grafana-Loki MCP Server

A FastMCP server that allows querying Loki logs from Grafana.

MCP Server Settings

json

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

GRAFANA_URL: URL of your Grafana instance
GRAFANA_API_KEY: Grafana API key with appropriate permissions

Features

Query Loki logs through Grafana API
Get Loki labels and label values
Format query results in different formats (text, JSON, markdown)
Support for both stdio and SSE transport protocols

Requirements

Python 3.10+
FastMCP
Requests

Installation

Using pip

bash

pip install grafana-loki-mcp

Development Setup

Clone this repository
Install dependencies using uv:

bash

# Install uv
pip install uv

# Create and activate virtual environment
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
uv pip install -e ".[dev]"

Usage

Environment Variables

Set the following environment variables:

GRAFANA_URL: URL of your Grafana instance
GRAFANA_API_KEY: Grafana API key with appropriate permissions

Command Line Arguments

You can also provide these values as command line arguments:

bash

grafana-loki-mcp -u https://your-grafana-instance.com -k your-api-key

Additional options:

--transport: Transport protocol to use (stdio or sse, default: stdio)

Running the Server

bash

# Using environment variables
export GRAFANA_URL=https://your-grafana-instance.com
export GRAFANA_API_KEY=your-api-key
grafana-loki-mcp

# Using command line arguments
grafana-loki-mcp -u https://your-grafana-instance.com -k your-api-key

# Using SSE transport
grafana-loki-mcp --transport sse

Development

Testing

Run the test suite:

bash

pytest

Run with coverage:

bash

pytest --cov=. --cov-report=term

Linting and Formatting

bash

# Run ruff linter
ruff check .

# Run black formatter
black .

# Run type checking
mypy .

Available Tools

query_loki

Query Loki logs through Grafana.

Parameters:

query: Loki query string
start: Start time (ISO format, Unix timestamp, or Grafana-style relative time like 'now-1h', default: 1 hour ago)
end: End time (ISO format, Unix timestamp, or Grafana-style relative time like 'now', default: now)
limit: Maximum number of log lines to return (default: 100)
direction: Query direction ('forward' or 'backward', default: 'backward')
max_per_line: Maximum characters per log line (0 for unlimited, default: 100)

get_loki_labels

Get all label names from Loki.

get_loki_label_values

Get values for a specific label from Loki.

Parameters:

label: Label name

format_loki_results

Format Loki query results in a more readable format.

Parameters:

results: Loki query results from query_loki
format_type: Output format ('text', 'json', or 'markdown', default: 'text')
max_per_line: Maximum characters per log line (0 for unlimited, default: 0)

Example Usage

python

# Example client code
from mcp.client import Client

async with Client() as client:
    # Query Loki logs with max_per_line limit
    results = await client.call_tool(
        "query_loki",
        {
            "query": '{app="my-app"} |= "error"',
            "limit": 50,
            "max_per_line": 100,  # Limit log lines to 100 characters
            "start": "now-6h",    # Grafana-style relative time: 6 hours ago
            "end": "now"          # Current time
        }
    )

    # Format the results
    formatted = await client.call_tool(
        "format_loki_results",
        {
            "results": results,
            "format_type": "markdown",
            "max_per_line": 100  # Can also limit at formatting time
        }
    )

    print(formatted)

License

This project is licensed under the MIT License - see the LICENSE file for details.

Star History

Repository Owner

tumf

User

Repository Details

Language Python

Default Branch main

Size 193 KB

Contributors 6

License MIT License

MCP Verified Nov 12, 2025

Programming Languages

Python

93.18%

Makefile

6.82%

Related MCPs

Discover similar Model Context Protocol servers

PMCP

Golang Model Context Protocol server for natural language Prometheus queries

PMCP implements a Model Context Protocol (MCP) server in Go, enabling natural language access and manipulation of Prometheus metrics. It maintains full consistency with the Prometheus HTTP API and supports a robust, type-safe interface for seamless integration with MCP-compatible clients. The server offers complete Prometheus API coverage and supports multiple transport methods, including HTTP and Server-Sent Events. Its modular architecture is designed for performance, extensibility, and effective error handling.

⭐ 3
MCP
yshngg/pmcp

VictoriaMetrics MCP Server

Model Context Protocol server enabling advanced monitoring and observability for VictoriaMetrics.

VictoriaMetrics MCP Server implements the Model Context Protocol (MCP) to provide seamless integration with VictoriaMetrics, allowing advanced monitoring, data exploration, and observability. It offers access to almost all read-only APIs, as well as embedded documentation for offline usage. The server facilitates comprehensive metric querying, cardinality analysis, alert and rule testing, and automation capabilities for engineers and tools.

⭐ 87
MCP
VictoriaMetrics-Community/mcp-victoriametrics

Gopher & Gemini MCP Server

A modern Model Context Protocol server for AI-driven exploration of Gopher and Gemini resources.

Gopher & Gemini MCP Server provides a secure and efficient bridge for AI assistants to interact with resources on vintage Gopher and modern Gemini protocols using the Model Context Protocol (MCP) standard. It is built with FastMCP, delivers structured JSON responses optimized for LLMs, and supports comprehensive protocol coverage with advanced security and performance features. The server implements robust safeguards, certificate validation, and works cross-platform with modern Python tooling.

⭐ 4
MCP
cameronrye/gopher-mcp

mcp-log-proxy

Web-based proxy for inspecting Model Context Protocol traffic in real time.

mcp-log-proxy enables users to observe and debug messages exchanged between MCP clients and servers through a user-friendly web interface. It supports the STDIO interface and can operate multiple proxy instances, each accessible via a web dashboard. The tool allows customization of ports, web page titles, and log file locations, making it suitable for managing and troubleshooting MCP-based model communication. Installation is straightforward via Homebrew or Go, and it supports real-time switching between different running proxies.

⭐ 26
MCP
emicklei/mcp-log-proxy

@dealx/mcp-server

MCP server enabling LLMs to search and interact with the DealX platform.

Implements the Model Context Protocol, providing a standardized interface for large language models to interact with the DealX platform. Supports searching for ads through structured prompts and is designed for easy integration with tools like Claude and VS Code extensions. Flexible configuration options are available for environment variables, logging, and deployment. Extensible architecture supports future feature additions beyond ad search.

⭐ 0
MCP
DealExpress/mcp-server

DuckDuckGo Search MCP Server

A Model Context Protocol server for DuckDuckGo web search and intelligent content retrieval.

DuckDuckGo Search MCP Server provides web search capabilities through DuckDuckGo, with advanced content fetching and parsing tailored for large language models. It supports rate limiting, error handling, and delivers results in an LLM-friendly format. The server is designed for seamless integration with AI applications and tools like Claude Desktop, enabling enhanced web search and content extraction through the Model Context Protocol.

⭐ 637
MCP
nickclyde/duckduckgo-mcp-server

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

Grafana-Loki MCP Server

Key Features

Use Cases

README

Grafana-Loki MCP Server

MCP Server Settings

Features

Requirements

Installation

Using pip

Development Setup

Usage

Environment Variables

Command Line Arguments

Running the Server

Development

Testing

Linting and Formatting

Available Tools

query_loki

get_loki_labels

get_loki_label_values

format_loki_results

Example Usage

License

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs