Uptrace MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UPTRACE_URL | Yes | The URL of your Uptrace instance (e.g., https://uptrace.xxx) | |
| UPTRACE_API_TOKEN | Yes | Your Uptrace API auth token | |
| UPTRACE_PROJECT_ID | Yes | The numeric ID of your Uptrace project |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| uptrace_search_spansA | Search spans with custom filters using Uptrace Query Language (UQL). Supports WHERE clauses, filters, and aggregations. Use 'where _status_code = "error"' to find error spans. |
| uptrace_get_traceB | Get all spans for a specific trace ID. Useful for debugging and understanding request flows. |
| uptrace_search_groupsA | Search and aggregate spans by groups. Supports GROUP BY operations and aggregations like count(), avg(), p99(), etc. |
| uptrace_search_servicesA | Search for services that have reported spans. Useful for discovering available services in the system. |
| uptrace_search_logsA | Search logs by text, severity, service name, or custom UQL query. Logs are represented as spans with _system = 'log:all'. |
| uptrace_get_query_syntaxA | Get UQL (Uptrace Query Language) syntax documentation. Returns operators, functions, examples, and common patterns for querying spans, logs, and metrics. |
| uptrace_get_alertB | Get details of a specific alert incident by ID. |
| uptrace_list_monitorsA | List all alerting monitors. Returns monitor IDs, names, types, and configuration. |
| uptrace_get_monitorC | Get details of a specific monitor by ID. |
| uptrace_list_dashboardsA | List all dashboards. Returns dashboard IDs and names. |
| uptrace_query_metricsA | Query metrics using UQL/PromQL-compatible syntax. Use this to retrieve metric values like CPU usage, request rates, etc. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose targeting specific resources and actions, such as getting alerts, monitors, traces, listing dashboards or monitors, and querying/searching different data types like metrics, logs, services, and spans. There is no overlap or ambiguity in functionality.
All tool names follow a consistent 'uptrace_verb_noun' pattern, using snake_case throughout, with verbs like get, list, query, and search clearly indicating actions. This uniformity makes the tool set predictable and easy to navigate.
With 11 tools, the server is well-scoped for monitoring and observability tasks, covering key operations like retrieving, listing, and querying various telemetry data. Each tool serves a specific purpose without redundancy, fitting the domain appropriately.
The tool set provides comprehensive coverage for the Uptrace domain, including CRUD-like operations for alerts, monitors, and traces, along with querying capabilities for metrics, logs, services, and spans. There are no obvious gaps, enabling agents to perform full monitoring and debugging workflows.