Grafana Loki
A server for querying Loki logs from Grafana.
Grafana-Loki MCP Server
A FastMCP server that allows querying Loki logs from Grafana.
MCP Server Settings
{
"mcpServers": {
"loki": {
"command": "uvx",
"args": [
"grafana-loki-mcp",
"-u",
"GRAFANA_URL",
"-k",
"GRAFANA_API_KEY"
]
}
}
}
GRAFANA_URL: URL of your Grafana instanceGRAFANA_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
pip install grafana-loki-mcp
Development Setup
- Clone this repository
- Install dependencies using uv:
# 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 instanceGRAFANA_API_KEY: Grafana API key with appropriate permissions
Command Line Arguments
You can also provide these values as command line arguments:
grafana-loki-mcp -u https://your-grafana-instance.com -k your-api-key
Additional options:
--transport: Transport protocol to use (stdioorsse, default:stdio)
Running the Server
# 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:
pytest
Run with coverage:
pytest --cov=. --cov-report=term
Linting and Formatting
# 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 stringstart: 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_lokiformat_type: Output format ('text', 'json', or 'markdown', default: 'text')max_per_line: Maximum characters per log line (0 for unlimited, default: 0)
Example Usage
# 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.
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Agent Passport System
Cryptographic identity, scoped delegation, values governance, and deliberative consensus for AI agents. 11 tools, Ed25519 signatures, zero blockchain.
Authless MCP Server
A template for creating a remote, authentication-free MCP server deployable on Cloudflare Workers.
Jira Context MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor.
Reference Servers
Reference implementations of Model Context Protocol (MCP) servers in Typescript and Python, showcasing MCP features and SDK usage.
Tuteliq
AI-powered safety tools for detecting grooming, bullying, threats, and harmful interactions in conversations. The server integrates Tuteliq’s behavioral risk detection API via the Model Context Protocol (MCP), enabling AI assistants to analyze interaction patterns rather than relying on keyword moderation. Use cases include platform safety, chat moderation, child protection, and compliance with regulations such as the EU Digital Services Act (DSA), COPPA, and KOSA.
MCP SysOperator
Manages Infrastructure as Code (IaC) operations using Ansible and Terraform. Requires external tools and manual setup.
Hello World MCP Server
A simple Hello World MCP server built with FastMCP, serving as a basic example.
MCP Servers Collection
A collection of MCP servers providing structured interfaces for AI assistants to interact with various development tools and services.
Second Opinion
Review commits and codebases using external LLMs like OpenAI, Google Gemini, and Mistral.
mcp-server template
A template for creating MCP (ModelContextProvider) servers, configurable via environment variables.