otel-analyzer-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {
"tasks": {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| load_traceA | Load a trace from file, string, X-Ray, or CloudWatch. Auto-detects format. Args: path: File path to trace JSON data: Raw JSON string trace_id: Trace ID to fetch from X-Ray or CloudWatch source: Source for trace_id lookup: 'xray' or 'cloudwatch' (default: xray) profile: AWS profile name region: AWS region |
| search_xrayC | Search X-Ray for traces matching filter expression. |
| search_genai_tracesA | Search CloudWatch aws/spans for GenAI traces from Bedrock AgentCore. Args: filter_query: CloudWatch Logs Insights filter (e.g., 'name like /bedrock/') start_time: ISO format start time end_time: ISO format end time limit: Max results (default: 20) profile: AWS profile name region: AWS region Returns GenAI traces with model info, token usage, and latency. |
| list_tracesA | List all loaded traces with summaries. |
| analyze_perfB | Analyze trace performance: latency breakdown, slow spans, critical path. |
| analyze_errsC | Analyze trace errors: error spans, exceptions, failure context. |
| summarize_traceD | High-level trace overview. |
| deep_analyzeC | Use MCP sampling for LLM-assisted trace analysis. |
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 8 tools
Each tool targets a distinct aspect of trace management and analysis. No two tools have overlapping purposes; descriptions clearly differentiate ingestion, listing, summarizing, error analysis, performance analysis, LLM-assisted analysis, and searching by source.
Tool names follow a consistent verb_noun snake_case pattern (e.g., load_trace, list_traces, summarize_trace). Minor deviations: analyze_errs and analyze_perf use abbreviations (errs, perf) and deep_analyze uses an adjective prefix, but these are still readable and fit the general pattern.
With 8 tools, the server provides a comprehensive but focused set of operations for trace analysis: ingestion, listing, summarization, error analysis, performance analysis, LLM-assisted analysis, and source-specific searches. Each tool earns its place without redundancy.
The tool set covers the main lifecycle of trace analysis: loading, listing, summarizing, error and performance analysis, and advanced LLM analysis. It also includes source-specific search. A minor gap is the lack of a query/filter capability on loaded traces beyond the static listing, but overall the surface is well-rounded for typical observability tasks.