Uptrace
Demo
Try it free Sign in
MCP

Ask your telemetry questions in plain text

Uptrace ships with a built-in Model Context Protocol server. Point Claude Code, Cursor, or Codex at your project and query spans, traces, alerts, and dashboards directly from your AI assistant, no dashboard clicking, no query language to learn first.

Connect your AI assistantSchedule a demo

14-day free trial · No credit card required

Connect in one command

Copy your project endpoint from Uptrace, add it to your AI assistant, and sign in through your browser. No SDK or separate integration is needed.

  • One command adds the server to Claude Code
  • Browser sign-in works with your existing Uptrace account, including SSO
  • The MCP page also offers an API token for clients without browser sign-in
  • Works with Claude, Cursor, Continue, and other MCP clients

Run in your terminal

Replace the project ID with yours, then sign in through your browser.

$claude mcp add --transport http uptrace https://api.uptrace.dev/mcp/<project_id>

Read spans and traces without writing UQL

Four tools cover everything from one slow request to aggregated error rates across a service, using the same search syntax and system filters as the Uptrace UI.

  • Inspect individual spans or aggregate them into groups with error rate and percentiles
  • Find whole traces with correlated sub-queries across multiple span types
  • Full search syntax: word, phrase, AND/OR/exclude, regex, scoped attribute search
  • System filters like httpserver:all, db:postgresql, and log:error
list_spans

Individual span records matching a query

list_span_groups

Spans aggregated with count, error rate, percentiles

list_traces

Whole traces via correlated sub-queries

list_trace_groups

Traces aggregated across multiple span types

Alerts and metrics as callable tools

An assistant can check what is currently firing, inspect a specific alert, and explore any metric, its attributes, and their values, without leaving the chat.

  • List alerts filtered by status, priority, type, or monitor
  • Get a single alert with full event history and assignees
  • List monitor rules with type, state, query, and channels
  • Discover metrics, their instrument type, unit, and attribute keys
list_alerts

Filter by status, priority, type, or monitor

get_alert

Full event history and assignees for one alert

list_monitors

Monitor rules, state, query, and channels

explore_metrics

Name, instrument, unit, and attributes

Create and update dashboards from a prompt

Dashboard tools use the same YAML schema as the UI import/export feature, so an assistant can scaffold a dashboard and you can still edit it by hand afterward.

  • List dashboards and tags already in the project
  • Export any dashboard as YAML, or start from a built-in template
  • Create or replace a dashboard definition in one call
  • Same YAML schema as manual dashboard import and export
get_dashboard_yaml

Export an existing dashboard as YAML

create_dashboard

Create a dashboard from a YAML definition

update_dashboard

Replace a dashboard with new YAML

list_dashboard_templates

Browse built-in starting points

Better together

Each signal is more powerful when correlated with the others. Uptrace stores traces, logs, and metrics in one place, no tool-switching, no data gaps.

Distributed tracing

Find the exact span that broke your request, across every service and database call.

Log management

Search structured logs at any scale and jump from any span to its logs in one click.

Metrics

PromQL-compatible metrics with no cardinality limits and automatic dashboards.

Common questions, clear answers

What is the Uptrace MCP server?
A built-in Model Context Protocol server that exposes your telemetry as MCP tools and resources. It lets AI assistants like Claude, Cursor, and Continue query spans, traces, metrics, and alerts, and manage dashboards, directly from a chat session instead of the Uptrace UI.
How do I authenticate MCP requests?
Use browser sign-in when your MCP client supports it. Uptrace issues an expiring OAuth grant for the selected project. Clients without browser sign-in can use an API token in the Authorization header.
Can an AI assistant modify my data, or only read it?
It depends on the tool and your permissions. Some tools only read telemetry; others can create or change monitors, dashboards, and incidents. Browser sign-in shows the access the client requests before you approve it.
Does the MCP server work if my organization uses SSO?
Yes. A client that supports browser sign-in opens the usual Uptrace login, where you can use your organization’s SSO provider, then asks you to approve its project access.
Which AI assistants can connect?
Any compatible MCP client can connect. The MCP project page shows commands for Claude Code and Codex with your project URL filled in, plus a token option for clients that need one.

Ready to let your AI assistant read the room?

Deploy in minutes with Docker. Open source. Fixed pricing. Your data stays on your infrastructure.

Connect your AI assistant

14-day free trial · No credit card required

Learn more

Documentation Pricing Schedule a demo