The request "cdebug" is ambiguous: it names no specific product, and the candidates cover different debugging tasks. The strongest matches for debugging production errors and issues are Sentry 1 and DebugBundle 7, with Sentry first for its established use and indexed debug actions 11; Langfuse 6 and MLflow 8 fit tracing-based debugging of LLM apps. Which platform or debugging target you mean (production errors, LLM traces, or Python tests) would sharpen the choice.
A question back: What do you want to debug: production errors in an application, LLM or agent traces, or Python tests?
- 1
Sentrysentry.ioverified and signed
Application performance monitoring and error tracking with an MCP server, CLI and SDKs; its sentry-debug-issue action finds an issue and pulls its stack trace, breadcrumbs and trace 11.
official:MCP server · @sentry/mcp-serverSDK · @sentry/nodeCLI · sentry-clirepository · sentry-pythonskill · sentry-cli+49 community tools built for it
for agents: sentry-debug-issue · sentry · sentry-fix-issues
- 2
DebugBundledebugbundle.comwebsite read, tools not yet checked
Captures production errors with their surrounding context into structured debug bundles for AI coding agents to investigate 7.
official:MCP server · DebugBundlepackage · DebugBundle+1 community tools built for it
- 3
Langfuselangfuse.comverified and signed
Open-source platform for tracing, observing and evaluating AI agents, with a Claude Code plugin that exports traces and session telemetry 16.
+29 community tools built for it
for agents: tracing · observability · langfuse-observability
- 4
MLflowmlflow.orgverified and signed
Open-source AI engineering platform for debugging, evaluating and monitoring LLM apps and agents, with an action to analyze a single MLflow trace by ID 18.
+6 community tools built for it
for agents: analyzing-mlflow-trace · analyzing-mlflow-session · retrieving-mlflow-traces
Sources
- 1Sentry Docs | Application Performance Monitoring & Error Tracking Softwaredocs.sentry.io · read 2026-10-29
- 6Langfuse: Open Source Agent Evals & Observabilitylangfuse.com · read 2026-10-29
- 7Production debugging for AI coding agents | DebugBundledebugbundle.com · read 2026-10-29
- 8MLflow - Open Source AI Platform for Agents, LLMs & Modelsmlflow.org · read 2026-10-29
- 11sentry-debug-issue: declares "sentry-debug-issue" (the record we read and signed)unfragile.ai · read 2026-10-24
- 16langfuse: declares "tracing" (the record we read and signed)unfragile.ai · read 2026-10-24
- 18analyzing-mlflow-trace: declares "analyzing-mlflow-trace" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
sentry-debug-issue · sentry-debug-issue verified and signed
Debug and fix a Sentry issue — find it (by link, ID, or search), pull full context (stack trace, breadcrumbs, trace, logs), optionally run Seer root-cause / autofix, apply the code fix, and resolve it via a `Fixes PROJECT-NAME-12A` commit/PR. Use when working a known error or hunting one down to fix
flowstudio-power-automate-debug · flowstudio-power-automate-debug verified and signed
Debug failing Power Automate cloud flows using the FlowStudio MCP server. The Graph API only shows top-level status codes. This skill gives your agent action-level inputs and outputs to find the actual root cause. Load this skill when asked to: debug a flow, investigate a failed run, why is this flo
debugging-streamlit · debugging-streamlit verified and signed
Debug Streamlit frontend and backend changes using make debug with hot-reload. Use when testing code changes, investigating bugs, checking UI behavior, or needing screenshots of the running app.
react-doctor · react-doctor verified and signed
Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.
unittest · pytest verified and signed
tracing · langfuse verified and signed
· DebugBundle website read, tools not yet checked
DebugBundle captures production errors and their context in structured debug bundles, giving AI coding agents reliable evidence to investigate.
analyzing-mlflow-trace · analyzing-mlflow-trace verified and signed
Analyzes a single MLflow trace to answer a user query about it. Use when the user provides a trace ID and asks to debug, investigate, find issues, root-cause errors, understand behavior, or analyze quality. Triggers on "analyze this trace", "what went wrong with this trace", "debug trace", "investig
dsql · dsql verified and signed
Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.
queryADatabase · Notion API verified and signed
Query a database
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.