$ loading_
Read LangSmith traces, run hierarchies, and URLs for LLM debugging and analysis.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "LangSmith MCP Server" yet — see the docs or source repo.
Query the most recent failed LangSmith runs, sorted by time descending. List each run's name, status, error message, and URL, then highlight the top 3 that should be investigated first.
A list of failed runs with error summaries, direct URLs, and prioritized investigation suggestions.
Read this LangSmith run and expand its children. Organize each step by hierarchy, including call names, execution order, and related URLs, so I can understand the full workflow.
A structured run hierarchy showing parent-child relationships and key access links.
Query a set of LangSmith traces and summarize common run patterns, repeatedly failing nodes, and suspicious trace URLs worth further inspection.
A summary of trace patterns, recurring problematic nodes, and recommended links to inspect.
Manage LangSmith traces, prompts, datasets, experiments, and billing with natural language.
Fetch and analyze LangSmith traces to debug LangChain and LangGraph agents.
Manage Langfuse projects, API keys, and traces through MCP locally.
Access ActivitySmith notifications and live activity tools for app integrations.
Let AI query and analyze OpenTelemetry traces to debug apps faster.
Quickly trace code relationships and execution paths with a single AI tool call.