MCP server · Developer tools
Jaeger MCP server
by mshegolev
Ask your AI about your app's traces in Jaeger: slow requests, errors, and which services call which.
This is a small helper that connects your AI assistant to Jaeger, a tool that records what happens inside your software when it runs. Once it is set up, you can ask questions in plain English about slow requests, errors, and how your services talk to each other. It is handy for developers, testers, and support engineers who look at trace data but do not want to click around a web page.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another app. This one connects your AI to Jaeger, the place where your app's trace data lives. So when you ask a question about a slow request, your AI can go look it up in Jaeger and bring the answer back to the chat.
What this MCP server does
You ask your AI something like which services are slow right now. Your AI passes that question to this helper program. The helper talks to your Jaeger server over the network, using the address and login details you set up. Jaeger sends back the trace data, and the helper hands it to your AI. Your AI then shows you a readable summary in the chat, with the numbers and names you asked for.
Click to zoomWhat you can do with it
- List all services that Jaeger is tracking
- Find traces with errors or slow requests in a service
- Show the full detail of one trace, span by span
- Compare two traces to see what changed
- Map which services call which other services
- Show latency and error rates per operation
- Spot unusual spikes in latency or errors
Try asking your AI
- “What services does Jaeger know about?”
- “Find traces with HTTP 500 errors in order-service from the last hour”
- “Show me the slowest traces over 2 seconds for GET /checkout”
- “What caused the error in trace abcdef1234567890?”
- “Map the service dependency graph for the last 7 days”
What it gives back to you
You get answers in the chat, usually as a short readable summary plus the underlying numbers. For a search, you get a list of traces with their IDs, durations, span counts, and error counts. For a single trace, you get the full span tree with service names, timings, and tags. For comparisons and statistics, you get tables or bullet points showing what changed and by how much.
Before you start
What you need
- A Jaeger server you can reach, and its web address (the query service URL)
- Login details for that Jaeger if it needs them: a bearer token, or a username and password
- Python installed if you use pip, or the uv tool if you use uvx
- The Claude desktop app or another AI app that supports MCP servers
Good to know
It only reads your trace data, so it cannot change or delete anything in Jaeger, but the trace details it shows may include internal service names, tags, and other information you would not want to share outside your team.
Install it with your AI
Add Jaeger MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Jaeger MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Developers, testers, SREs, and support engineers who already use Jaeger and want to ask questions about traces without leaving their AI chat.
