{"slug":"langchain-ai/langsmith-mcp-server","name":"LangSmith MCP Server","description":"An MCP server for fetching conversation history and prompts from the LangSmith observability platform.","category":"development","tags":[],"official":false,"stars":113,"transport":"stdio","install":[{"cmd":"npx @modelcontextprotocol/inspector@latest","imports":[]}],"tools":[{"name":"get_thread_history","description":"Retrieve message history for a conversation thread. Uses char-based pagination: pass page_number (1-based), and use returned total_pages to request more pages. Optional max_chars_per_page and preview_chars control page size and long-string truncation."},{"name":"list_prompts","description":"Fetch prompts from LangSmith with optional filtering by visibility (public/private) and limit."},{"name":"get_prompt_by_name","description":"Get a specific prompt by its exact name, returning the prompt details and template."},{"name":"push_prompt","description":"Documentation-only: how to create and push prompts to LangSmith."},{"name":"fetch_runs","description":"Fetch LangSmith runs (traces, tools, chains, etc.) from one or more projects. Supports filters (run_type, error, is_root), FQL (filter, trace_filter, tree_filter), and ordering. When trace_id is set, returns char-based paginated pages; otherwise returns one batch up to limit. Always pass limit and page_number."},{"name":"list_projects","description":"List LangSmith projects with optional filtering by name, dataset, and detail level (simplified vs full)."},{"name":"list_datasets","description":"Fetch datasets with filtering by ID, type, name, name substring, or metadata."},{"name":"list_examples","description":"Fetch examples from a dataset by dataset ID/name or example IDs, with filter, metadata, splits, and optional as_of version."},{"name":"read_dataset","description":"Read a single dataset by ID or name."},{"name":"read_example","description":"Read a single example by ID, with optional as_of version."},{"name":"create_dataset","description":"Documentation-only: how to create datasets in LangSmith."},{"name":"update_examples","description":"Documentation-only: how to update dataset examples in LangSmith."},{"name":"list_experiments","description":"List experiment projects (reference projects) for a dataset. Requires reference_dataset_id or reference_dataset_name. Returns key metrics (latency, cost, feedback stats)."},{"name":"run_experiment","description":"Documentation-only: how to run experiments and evaluations in LangSmith."},{"name":"get_billing_usage","description":"Fetch organization billing usage (e.g. trace counts) for a date range. Optional workspace filter; returns metrics with workspace names inline."}],"env_vars":["LANGSMITH_API_KEY","LANGSMITH_WORKSPACE_ID","LANGSMITH_MONITORING_API_KEY","LANGSMITH_MONITORING_WORKSPACE_ID"],"auth_type":"none","github":"https://github.com/langchain-ai/langsmith-mcp-server","homepage":"","server_url":"","status":"active","source":"mcpservers.org","updated_at":"Thu May 28"}