Graylog MCP Server
Enables AI assistants to query and analyze logs from Graylog instances using universal search with relative or absolute time windows, supporting both full result retrieval and lightweight count-only queries.
README
Graylog MCP Server
Introduction
The Graylog MCP Server lets AI IDEs and agents securely query your Graylog instance via the Model Context Protocol. It exposes standardized tools so assistants can search recent or absolute time windows and optionally count results without pulling full payloads.
What you get:
- search tools for Graylog universal search
- relative window: last N seconds
- absolute window: explicit ISO timestamps
- count-only variants for lightweight analytics
- drop-in configuration for popular IDEs and MCP tools
Requirements:
- a reachable Graylog URL
- credentials with permissions to use Universal Search
Links:
- Model Context Protocol: https://modelcontextprotocol.io
- Graylog: https://www.graylog.org/
Installation and Usage
Quick start (runs the MCP server over stdio):
npx -y graylog-mcp
Required environment variables:
- GRAYLOG_BASE_URL: your Graylog base URL (e.g., https://graylog.example/)
- GRAYLOG_USERNAME: Graylog username
- GRAYLOG_PASSWORD: Graylog password
Configure in your IDE or Agentic Tool of choice (Cursor, VS Code, Claude Code):
{
"graylog": {
"command": "npx -y graylog-mcp",
"env": {
"GRAYLOG_BASE_URL": "https://YOUR_GRAYLOG_INSTANCE_URL/",
"GRAYLOG_USERNAME": "YOUR_USERNAME",
"GRAYLOG_PASSWORD": "YOUR_PASSWORD"
}
}
}
Sample Usage Prompts
Some sample prompts to make the most of the MCP server:
Analyzing error patterns
search graylog for the errors in the past 24 hours with log_level:ERROR with a max limit of 100 per query
use the message patterns in the query results to figure out the patterns of errors that are occuring and put them in ERRORS.md
for subsequent queries, use the NOT condition to filter out messages with error patterns that are already discovered
Security notes:
- Prefer scoped, least-privilege Graylog credentials.
- Do not commit secrets to source control; use environment managers where possible.
Contribution and Local Development
Prerequisites:
- Bun: https://bun.sh/
- Node-compatible environment
Install and build:
# Install deps (if any) and build
bun install
bun run build
Run locally (TypeScript directly via Bun stdio):
# Start the MCP server from source
export GRAYLOG_BASE_URL="https://your-graylog.example/"
export GRAYLOG_USERNAME="your-user"
export GRAYLOG_PASSWORD="your-password"
bun index.ts
Test against a live Graylog (verifies universal search endpoints):
export GRAYLOG_BASE_URL="https://your-graylog.example/"
export GRAYLOG_USERNAME="your-user"
export GRAYLOG_PASSWORD="your-password"
# Run verification (Bun executes TypeScript directly)
bun run test:graylog
Project scripts:
- build:
bun run build→ emitsdist/index.js - test:
bun run test:graylog→ health checks for relative/absolute universal search - show-package-name: prints the package name
Debug with MCP Inspector against local source:
npx -y @modelcontextprotocol/inspector "bun index.ts"
Code style and contributions:
- Keep code readable and well-typed; avoid unnecessary complexity.
- Match existing formatting; keep lines reasonably wrapped.
- Open issues/PRs with clear reproduction steps or proposed changes.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.