L
LangSmith MCP
42
Stack Score
Editorial pick✓ Verified workingMCP server
LangSmith MCP
LangSmith trace + eval + dataset ops.
Best for
Best for AI engineering teams running LangSmith observability.
At a glance
- Pricing
- open-source
- Setup time
- 15 minutes
- Learning curve
- easy
- Last verified
- 5/26/2026
What we love
- ✓LangChain-maintained
- ✓Strong LLM-app tracing
- ✓Dataset + eval surface
Where it falls short
- −LangSmith plan required
- −Best inside LangChain stack
- −Per-trace pricing
Pricing
✓ Pricing verified Jun 14, 20261 tier
Open-source
$0
perpetual
- ✓MIT
Overview
MCP server for LangSmith — trace + run query, dataset + eval ops, project mgmt. Lets Claude query LLM-app observability data.
Key features
- ●Trace + run query
- ●Dataset + eval ops
- ●Project + tag mgmt
- ●API key auth
- ●LangChain-native
Best use cases
LLM-app debugging
Let Claude query LangSmith traces during incident investigation.
Eval-driven dev
Run + analyze evals across LLM apps via Claude.
Integrations
Similar tools
See all analytics →One AI Stack pick every week.
The tool we’d pay for this week, why we’d pay for it, and what we’d skip. No promo spam.