Tracehub MCP

Query OTel traces across Jaeger, Tempo, Traceloop, Datadog, Sentry, X-Ray, New Relic, Honeycomb.

Connector by mcpsmiths · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mcpsmiths-tracehub-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Query OTel traces across Jaeger, Tempo, Traceloop, Datadog, Sentry, X-Ray, New Relic, Honeycomb.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools: 15 read · 0 write · 0 delete · 4 not yet classified
Secrets: 2 (API keys, tokens or passwords)
Install scripts: None found
Runs as: Python package

Tools by what they do 19

Read from the source code; the running server may list different tools.

Read 15 · Look things up without changing anything.

compare_time_windows
find_errors
get_llm_expensive_traces
get_llm_model_stats
get_llm_slow_traces
get_llm_usage
get_prompt_version_stats
get_session_stats
get_trace
list_llm_models
list_llm_tools_tool
list_services

Show 3 more tools

list_sessions
search_spans_tool
search_traces

Not yet classified 4 · We could not tell from the name and description.

correlate_trace
investigate_cost_spike
investigate_error_spike
triage_trace

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

BACKEND_API_KEY
BACKEND_APP_KEY

Other settings (environment variables or headers).

BACKEND_AWS_REGION
BACKEND_ENVIRONMENTS
BACKEND_HONEYCOMB_DATASET
BACKEND_MAX_RESPONSE_BYTES
BACKEND_NEWRELIC_ACCOUNT_ID
BACKEND_SENTRY_ORG
BACKEND_SENTRY_PROJECT
BACKEND_TEMPO_INSTANCE_ID
BACKEND_TIMEOUT
BACKEND_TYPE
BACKEND_URL
LOG_LEVEL

Show 7 more settings

MAX_TRACES_PER_QUERY
MCP_INCLUDE_ARGS_IN_SPANS
OTEL_EXPORTER_OTLP_ENDPOINT
OTEL_SERVICE_NAME
QUERY_CACHE_MAX_ENTRIES
QUERY_CACHE_TTL_SECONDS
SLOW_REQUEST_THRESHOLD_MS

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

compare_time_windowsCompare Time Windows
Compare aggregated LLM usage metrics between two time windows. Runs the same usage aggregation for both ranges and returns the delta - useful for "this week vs last week" or "before/after a deploy" style comparisons of request/token counts. Args: range_a_start: Range A start time in ISO 8601 format range_a_end: Range A end time in ISO 8601 format range_b_start: Range B start time in ISO 8601 format range_b_end: Range B end time in ISO 8601 format service_name: Filter by service name (applied to both ranges) gen_ai_system: Filter by LLM provider (applied to both ranges…
correlate_traceCorrelate Trace
Try to find the corresponding trace in a second, independently- configured backend (e.g. a Datadog trace and its downstream Sentry error, joined) - given a trace_id known to the primary backend. Tries a direct trace_id match in the secondary backend first (confidence "high"); if that fails, falls back to a time-window + service-name-overlap heuristic search (confidence "low"). This is a best-effort correlation, not a guaranteed join - see the always-present `limitations` in the result for why. Requires a secondary backend to be configured via SECONDARY_BACKEND_TYPE/SECONDARY_BACKEND_URL (and …
find_errorsFind Errors
Find traces with errors. Including detailed error messages, stack traces, and LLM-specific error information. Args: start_time: Start time in ISO 8601 format end_time: End time in ISO 8601 format service_name: Filter by service name limit: Maximum error traces to return (default: 100) Returns: JSON string with error traces
get_llm_expensive_tracesGet LLM Expensive Traces
Find traces with highest LLM token usage. Useful for cost optimization and identifying inefficient prompts. Args: limit: Maximum number of traces to return (default: 10) start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_tokens: Minimum token count threshold (only return traces above this) service_name: Filter by service name gen_ai_request_model: Filter by requested model name (e.g., "gpt-4") gen_ai_response_model: Filter by actual model used (e.g., "gpt-4-0613") Returns: JSON string with top N mo…
get_llm_model_statsGet LLM Model Stats
Get detailed performance statistics for a specific LLM model. Analyzes request count, latency percentiles (p50, p95, p99), token usage statistics, error rates, and finish reason distributions. Args: model_name: Model name to analyze (e.g., "gpt-4", "claude-3-opus", "gpt-3.5-turbo") start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name limit: Maximum traces to analyze (default: 1000, capped by MAX_TRACES_PER_QUERY / --max-traces-per-query) Returns: JSON string with comprehensiv…
get_llm_slow_tracesGet LLM Slow Traces
Find slowest LLM traces by duration. Useful for performance optimization and identifying latency bottlenecks. Args: limit: Maximum number of traces to return (default: 10) start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_duration_ms: Minimum duration threshold in milliseconds (only return traces above this) service_name: Filter by service name gen_ai_request_model: Filter by requested model name (e.g., "gpt-4") gen_ai_response_model: Filter by actual model used (e.g., "gpt-4-0613") Returns: JSON …
get_llm_usageGet LLM Usage
Get aggregated LLM usage metrics (token counts) for a time period. Provides breakdowns by model and service. Args: start_time: Start time in ISO 8601 format end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider gen_ai_request_model: Filter by requested model name gen_ai_response_model: Filter by actual model used limit: Maximum traces to analyze (default: 1000) Returns: JSON string with usage metrics
get_prompt_version_statsGet Prompt Version Stats
Get aggregated performance stats grouped by prompt name and version. Groups spans by gen_ai.prompt.name + gen_ai.prompt.version, mirroring Langfuse's shipped per-prompt Metrics tab. Real-world adoption of these two attributes is still thin, so this tool may often return an empty list until more instrumentations populate them. Args: start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider (openai, anthropic, etc.) limit: Maximum spans to analyze (d…
get_session_statsGet Session Stats
Get detailed statistics for a single conversation/session. Analyzes span count, distinct services, time bounds, LLM request/success/ error counts, latency percentiles, and token usage for every span sharing the given gen_ai.conversation.id. Args: conversation_id: The gen_ai.conversation.id to analyze start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name limit: Maximum spans to analyze (default: 1000) Returns: JSON string with comprehensive session statistics
get_traceGet Trace
Get complete trace details by trace ID. Returns all spans with attributes, including parsed Opentelemetry data for LLM operations. Args: trace_id: Trace identifier detail_level: "full" (default) returns every attribute/event value in full, unchanged from this tool's original behavior. "summary" elides known-large gen_ai.* fields (input/output messages, system instructions, retrieval documents) and truncates long event-attribute values, for callers that don't need full prompt/completion bodies. Returns: TraceDetail with complete trace data
investigate_cost_spikeInvestigate Cost Spike
Investigate an LLM cost spike: compare a recent window against a baseline and rank which models/services contributed most to the change. On-request/pull-based analysis, not a push alert - mirrors SigNoz's own "investigate telemetry cost" skill. Call this when you suspect (or want to check for) a cost increase, rather than polling get_llm_usage by hand. Args: recent_start: Recent window start time in ISO 8601 format recent_end: Recent window end time in ISO 8601 format baseline_start: Baseline window start (ISO 8601). If omitted along with baseline_end, auto-computed as th…
investigate_error_spikeInvestigate Error Spike
Investigate an error-rate spike: compare a recent window against a baseline and rank which services/models/error types contributed most. is_spike requires both an absolute error-count floor and a relative rate-multiplier to hold, so a tiny sample (e.g. 1 error becoming 2) doesn't read as a spike. Args: recent_start: Recent window start time in ISO 8601 format recent_end: Recent window end time in ISO 8601 format baseline_start: Baseline window start (ISO 8601). If omitted along with baseline_end, auto-computed as the same duration immediately preceding recent_star…
list_llm_modelsList LLM Models
List all LLM models being used with usage statistics. Discovers what models are deployed and tracks their usage patterns. Args: start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider (e.g., openai, anthropic, cohere) limit: Maximum traces to analyze for model discovery (default: 1000) Returns: JSON string with list of models and their statistics (count, request_count, first_seen, last_seen)
list_llm_tools_toolList LLM Tools
List all LLM tools being used by identifying traceloop.span.kind == tool. Discovers which tools/functions LLM applications are calling, grouped by tool name with usage statistics. Args: start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider (openai, anthropic, etc.) limit: Maximum spans to analyze (default: 1000) Returns: JSON string with list of tools and their statistics (usage count, services, first/last seen)
list_servicesList Services
List all available services in the OpenTelemetry backend. Returns: JSON string with list of services

Show 4 more tools

list_sessionsList Sessions
List conversations/sessions grouped by gen_ai.conversation.id. Groups spans that carry the gen_ai.conversation.id attribute (a real, cross-industry OTel semantic convention for session/conversation grouping) to surface per-conversation span counts, token usage, and time bounds - useful for understanding multi-turn conversation activity. Args: start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider (openai, anthropic, etc.) limit: Maximum spans to…
search_spans_toolSearch Spans
Search for individual OpenTelemetry spans with optional filters. Unlike search_traces, this returns individual spans rather than grouped traces, which is useful for analyzing specific operations or finding spans with certain characteristics (e.g., LLM tool calls with traceloop.span.kind == tool). Args: service_name: Filter by service name operation_name: Filter by operation/span name start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_duration_ms: Minimum span duration in milliseconds max_duration_ms: Maximu…
search_tracesSearch Traces
Search for OpenTelemetry traces with filters. Supports both simple parameters and advanced generic filter system. Args: service_name: Filter by service name (use filters for advanced queries) operation_name: Filter by operation/span name start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_duration_ms: Minimum trace duration in milliseconds max_duration_ms: Maximum trace duration in milliseconds gen_ai_system: Filter by LLM provider (e.g., openai, anthropic) gen_ai_request_model: Filter by requested m…
triage_traceTriage Trace
Synthesize a likely-root-cause diagnosis for a trace, instead of returning raw trace data for the caller to re-derive one from every time. Computes a critical path (the "Last Finishing Child" chain actually responsible for the trace's total latency), ranks spans by self-time (latency contribution net of children, top 10), and - when the trace contains an error anywhere under any root span - identifies the deepest error span in the trace's error chain as the likely root cause. Falls back to the highest self-time span as a pure-latency diagnosis when no error is present. Deterministic (no LLM c…

Compare and alternatives

Featured in

Best MCP servers for observability

Signals

Stars: 0
Forks: 0
Open issues: 8
Weekly downloads: 209
Last commit: Oct 14, 2026 (14 days ago)
Last release: Oct 14, 2026 (14 days ago)
Last package publish: Oct 14, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.mcpsmiths/tracehub-mcp
Version: 0.13.0
Auth: API key
Packages: pypi tracehub-mcp
License: Apache-2.0
Repository: github.com/mcpsmiths/tracehub-mcp
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql