# LangSmith API + MCP (slim)

> LangChain's hosted tracing, evaluation, prompt hub and dataset platform, framework-agnostic with Python and TypeScript SDKs and OpenTelemetry ingest.

- Full: https://www.anchorterminal.com/tools/langsmith.md (~6,900 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/langsmith.json · canonical https://www.anchorterminal.com/tools/langsmith
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**BB · 71.3/100 · rank #85 of 452 · #3 in Agent observability & evals · agent-ready · confidence medium**


Assessment: Rate limits published per endpoint and per plan, with each kind of 429 explained. Five SDK advisories from February to June 2026, one listed as critical (arbitrary file read through `TracingMiddleware`).

## Facts

- Kind: HTTP API · vendor: LangChain · category: Agent observability & evals · legal entity: LangChain, Inc. · provenance 86/100
- Endpoint: `https://api.smith.langchain.com` (HTTP, Streamable HTTP)
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: MIT (SDK only, platform closed source)
- Probe metrics: not measured yet (probes haven't run)
- Free tier: Developer, 1 seat, 5,000 base traces a month, no payment method needed
- Rate limits: Per key a minute, 5,000 run writes, 5,000 feedback writes, 30 `GET /runs/:id`, 30 session deletes and 2,000 other calls. Hourly ingest 50,000 events and 500 MB on Developer without a card, 250,000 and 2.5 GB with one, 500,000 events on Plus. Custom on Enterprise
- What appears in a trace: Nested runs for chains, LLM calls, tools and retrievers with inputs, outputs, tokens, cost, errors and feedback, from the SDKs, LangChain callbacks or OpenTelemetry (vendor's description)
- Evaluations: Datasets with versions, offline experiments via SDK, online evaluators, pairwise comparison, annotation queues and tuned evaluators (US Cloud only)
- MCP server: Hosted remote MCP per region, streamable HTTP, OAuth 2.1 or `X-Api-Key`. About 16 tools covering threads, prompts, runs, datasets, experiments and billing. The write-named tools return how-to text, so it only reads. Also on self-hosted v0.15 and later
- Data retention: 14 days for base traces, 180 days for extended traces on SaaS since 2026-09-14
- LLM gateway: Pay-as-you-go model usage through prepaid gateway credits at face value plus a 3.5% processing fee
- Open source: SDKs and the standalone MCP server are MIT. The platform isn't open source, self-hosting needs an Enterprise licence
- Prices: Plus plan $39 per seat per month; Base traces $5 per 1,000 requests; Extended trace upgrade $2.50 per 1,000 requests; LangChain Compute Unit $1.50 per compute unit
- 2026-09-14 Notice: Extended-retention traces on SaaS capped at 180 days

- Scores: Reliability 81, Performance pending, Schema & documentation 86, Agent ergonomics 76, Security & auth 77, Payments & pricing 40, Task success pending, Maintenance & community 85, Transparency & trust 78 · negative events -4 · total over the 7 assessed categories
- Why: Reliability, incident.io status page per region with 11 components on GCP US (20). · Schema & documentation, Public OpenAPI 3.1 at api.smith.langchain.com/openapi.json with well over 100 paths, deprecated operations flagged (25). · Agent ergonomics, The remote MCP lists 15 tools in its docs, and the changelog has since added `list_model_price_maps` and Engine issue tools, so roughly 16 t… · Security & auth, Personal access tokens inherit the user's permissions. · Payments & pricing, No x402 or other machine payment (0). · Maintenance & community, Python SDK v0.14.2 on 2026-09-30, with v0.14.3 and JS 0.10.7 following on 2 October (30). · Transparency & trust, Closed platform.
- Sources: 14, open questions: 4, both in the full twin
- Capabilities: obs.traces, obs.evals, obs.prompts, obs.datasets, obs.gateway
- JSON: https://www.anchorterminal.com/api/v1/tools/langsmith.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/langsmith.svg` or a link to https://www.anchorterminal.com/tools/langsmith from a page on langchain.com or one of its subdomains, or the README of github.com/langchain-ai/langsmith-sdk, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Batch run reads. `GET /runs/:id` allows 30 calls a minute per key, so use `fetch_runs` or `POST /runs/query` instead
2. Pass `trace_id` or `min_start_time` to `fetch_runs` and keep `limit` low. Results page by a 25,000-character budget
3. Don't call `create_dataset` or `run_experiment` over MCP to make changes. They return how-to text, not results
4. Send `X-Api-Key` and point at the regional host (eu., apac. or aws.api.smith.langchain.com) that matches the workspace
5. Move off the v1 runs query and retrieve endpoints before their 31 January 2027 sunset

## Connect

```bash
curl https://api.smith.langchain.com/api/v1/sessions -H "X-Api-Key: $LANGSMITH_API_KEY"
```

```bash
claude mcp add --transport http langsmith https://api.smith.langchain.com/mcp
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/langsmith

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Respan API + MCP | B | 65.9 | obs.traces, obs.evals, obs.prompts, obs.gateway, obs.datasets | https://www.anchorterminal.com/tools/respan.min.md |
| Braintrust API + MCP | C | 61.3 | obs.traces, obs.evals, obs.prompts, obs.gateway, obs.datasets | https://www.anchorterminal.com/tools/braintrust.min.md |
| Helicone AI Gateway + MCP | D | 47.1 | obs.traces, obs.gateway, obs.prompts, obs.datasets, obs.evals | https://www.anchorterminal.com/tools/helicone.min.md |
| Arize Phoenix | BB | 75.6 | obs.traces, obs.evals, obs.prompts, obs.datasets | https://www.anchorterminal.com/tools/arize-phoenix.min.md |
| Langfuse API + MCP | BB | 72.8 | obs.traces, obs.evals, obs.prompts, obs.datasets | https://www.anchorterminal.com/tools/langfuse.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ Six months promised, a week given on retention (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★☆☆ Four tools named like actions that only explain (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial)