Loki MCP
Debug and investigate app issues using AI and Grafana Loki
Loki MCP Server
Query Grafana Loki logs directly from AI agents using the Model Context Protocol (MCP).
Built in Go. Enables AI-powered log analysis using LogQL.
Supports integration with:
- Claude Desktop
- AI agent frameworks
- automation tools
- DevOps workflows
Motivation
The official grafana/loki-mcp exposes a single loki_query tool, which means the LLM must already know valid label names and values before it can build a query. This project takes a different approach by providing 5 granular tools — labels, label_values, and series let the LLM discover what's available in Loki first, then construct precise query_range or query calls. The result is more accurate log retrieval with fewer wasted round-trips.
Additionally, this server enforces strict input validation (limit caps, direction validation, label name format checks, mutually exclusive auth) to surface errors early instead of forwarding bad requests to Loki.
Features
- query_range — Execute LogQL range queries to fetch logs over a time window
- query — Execute LogQL instant queries for point-in-time evaluation
- labels — List all available label names
- label_values — List values for a specific label
- series — Find active log stream series matching a selector
Installation
Homebrew
brew install incu6us/tap/loki-mcp-server
Go install
go install github.com/incu6us/loki-mcp-server/cmd/loki-mcp-server@latest
Or build from source:
git clone https://github.com/incu6us/loki-mcp-server.git
cd loki-mcp
go build -o loki-mcp-server ./cmd/loki-mcp-server
Configuration
The server is configured entirely via environment variables, injected by the MCP client.
| Variable | Required | Default | Description |
|---|---|---|---|
LOKI_URL | yes | — | Base URL of the Loki instance |
LOKI_USERNAME | no | — | Basic auth username |
LOKI_PASSWORD | no | — | Basic auth password |
LOKI_BEARER_TOKEN | no | — | Bearer token authentication |
LOKI_TLS_SKIP_VERIFY | no | false | Skip TLS certificate verification |
LOKI_TENANT_ID | no | — | X-Scope-OrgID header for multi-tenant deployments |
LOKI_HTTP_TIMEOUT | no | 30s | HTTP request timeout (Go duration, e.g. 10s, 1m) |
Note: Basic auth (
LOKI_USERNAME/LOKI_PASSWORD) and bearer token (LOKI_BEARER_TOKEN) are mutually exclusive.
Usage with Claude Code
Add to your Claude Code MCP configuration (~/.claude.json):
{
"mcpServers": {
"loki-mcp-server": {
"type": "stdio",
"command": "/path/to/loki-mcp-server",
"args": [],
"env": {
"LOKI_URL": "http://loki:3100",
"LOKI_USERNAME": "admin",
"LOKI_PASSWORD": "secret"
}
}
}
}
Usage with Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"loki-mcp-server": {
"type": "stdio",
"command": "/path/to/loki-mcp-server",
"args": [],
"env": {
"LOKI_URL": "http://loki:3100",
"LOKI_USERNAME": "admin",
"LOKI_PASSWORD": "secret"
}
}
}
}
Tools
query_range
Execute a LogQL range query against Loki to fetch logs over a time window.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
query | string | yes | — | LogQL query expression |
start | string | no | 1 hour ago | Start of time range (RFC3339 or Unix nano) |
end | string | no | now | End of time range |
limit | number | no | 100 | Max entries (max 5000) |
direction | string | no | backward | forward or backward |
query
Execute a LogQL instant query for point-in-time evaluation.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
query | string | yes | — | LogQL query expression |
limit | number | no | 100 | Max entries (max 5000) |
time | string | no | now | Evaluation timestamp |
direction | string | no | backward | forward or backward |
labels
List all available label names in Loki.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
start | string | no | 6 hours ago | Start of time range |
end | string | no | now | End of time range |
label_values
List values for a specific label.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
label | string | yes | — | Label name |
start | string | no | 6 hours ago | Start of time range |
end | string | no | now | End of time range |
series
Find active log stream series matching a selector.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
match | string | yes | — | Stream selector (e.g. {app="nginx"}) |
start | string | no | 6 hours ago | Start of time range |
end | string | no | now | End of time range |
Local Development Stack
A Docker Compose setup is included under deploy/ to spin up a full Loki environment for testing:
- Loki — log storage at
http://localhost:3100 - Grafana — UI at
http://localhost:3000(anonymous admin, Loki pre-configured as datasource) - Promtail — collects container logs and ships them to Loki
- Log generator — emits structured JSON logs with randomized apps (
nginx,api,gateway,auth,payments), levels, and messages
# Start the stack
docker compose -f deploy/docker-compose.yml up -d
# Use loki-mcp-server against local Loki
LOKI_URL=http://localhost:3100 loki-mcp-server
# Stop the stack
docker compose -f deploy/docker-compose.yml down
Development
# Run tests
go test ./...
# Build
go build -o loki-mcp-server ./cmd/loki-mcp-server
# Vet
go vet ./...
⭐ If this project is useful for you, please star the repository.
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
CoinAPI MCP Server
Access real-time and historical crypto market data from CoinAPI’s MCP server, built for developers and AI agents needing reliable, unified market coverage.
Mermaid
Generate mermaid diagram and chart with AI MCP dynamically.
Airflow MCP Server
Control Apache Airflow via its API using JWT authentication.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)
Persona MCP Server
Dynamically manage AI personas from markdown files for AI assistants like Claude.
DINO-X
Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
Codebase MCP Server
An intelligent codebase search engine that transforms local codebases into a natural language queryable knowledge base.
Developer Tools MCP Server
Developer resources including GitHub, npm, PyPI, Docker Hub, GitLab, and StackOverflow
Roblox MCP
Connect AI coding agents to a live Roblox Studio session.
OpenTofu MCP Server
A Model Context Protocol (MCP) server for accessing the OpenTofu Registry.