# Laminar API + MCP (slim)

> Open-source tracing, evaluations and an agent debugger built on OpenTelemetry, with browser session recordings synced to traces for browser agents.

- Full: https://www.anchorterminal.com/tools/laminar.md (~5,950 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/laminar.json · canonical https://www.anchorterminal.com/tools/laminar
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**C · 57/100 · rank #298 of 452 · #6 in Agent observability & evals · not agent-ready · confidence medium**


Assessment: Browser session recordings can be matched to agent traces. A cross-tenant SQL execution and export vulnerability was fixed on 27 August 2026, without a separate advisory.

## Facts

- Kind: HTTP API · vendor: Laminar (LMNR AI) · category: Agent observability & evals · legal entity: LMNR AI, Inc. · provenance 75/100
- Endpoint: `https://api.lmnr.ai/v1` (HTTP, Streamable HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: Apache-2.0
- Probe metrics: not measured yet (probes haven't run)
- Free tier: 1 GB of data, 7 days of retention, 1 project, 1 seat, $2.50 of Signals credit
- Rate limits: Not published
- What appears in a trace: Spans from auto-instrumented LLM SDKs and agent frameworks, tool calls, sessions, user IDs, costs and browser recordings. OTLP ingestion for anything else (vendor's description)
- Evaluations: SDK evaluations against datasets, run comparison, labelling queues, and a debugger that records and replays agent runs with cached steps
- MCP server: Hosted at `https://api.lmnr.ai/v1/mcp`, streamable HTTP, Bearer project key. 3 tools, SQL is read-only. Also served by self-hosted instances
- Data retention: 7 days on Free, 30 days on Starter, 6 months on Pro, custom on Enterprise
- Open source: Apache-2.0. Docker Compose runs frontend, app server, Postgres, ClickHouse and Quickwit. Helm adds RabbitMQ and Redis
- Compliance: SOC 2 Type II, HIPAA and server-side PII redaction listed on the pricing page (vendor's claim)
- Prices: Starter plan $30 per month (plan); Pro plan $150 per month (plan); Extra data on Starter $2 per GB of traffic; Extra data on Pro $1.50 per GB of traffic

- Scores: Reliability 50, Performance pending, Schema & documentation 88, Agent ergonomics 80, Security & auth 45, Payments & pricing 30, Task success pending, Maintenance & community 83, Transparency & trust 66 · negative events -5 · total over the 7 assessed categories
- Why: Reliability, Better Stack page at status.laminar.sh, but its only components are the homepage and an API echo probe, with nothing for ingestion, SQL or M… · Schema & documentation, OpenAPI in the docs, and the MCP tools take typed schemas generated from Rust structs (25). · Agent ergonomics, Three MCP tools, but the SQL tool's description embeds the whole table schema, so the list costs more context than the count suggests (18). · Security & auth, One project API key as a Bearer token, revocable, scoped to one project, with no read-only key type (20). · Payments & pricing, No x402 (0). · Maintenance & community, TypeScript SDK 0.8.49 on 2026-09-23, Python SDK 0.7.64 on 2026-09-21 and server v0.2.5 on 2026-09-13, with commits on the dev branch on 1 Oc… · Transparency & trust, Apache-2.0, with Signals and Slack alerts held back from the open-source images behind a licence key (28).
- Sources: 10, open questions: 4, both in the full twin
- Capabilities: obs.traces, obs.evals, obs.datasets
- JSON: https://www.anchorterminal.com/api/v1/tools/laminar.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/laminar.svg` or a link to https://www.anchorterminal.com/tools/laminar from a page on laminar.sh or one of its subdomains, or the README of github.com/lmnr-ai/lmnr, 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. Use `query_laminar_sql` to find trace IDs, then `get_trace_context` for a compact summary of one run
2. Always add a time range and `LIMIT` to SQL. Server caps on time, memory and result size reject wide scans
3. On 429 from the SQL API, back off. The per-project limit isn't published
4. Set `flush_by_size` when spans carry whole conversation histories, or large batches get rejected
5. Keep the project API key in a header, not in the URL

## Connect

```bash
curl https://api.lmnr.ai/v1/project -H "Authorization: Bearer $LMNR_PROJECT_API_KEY"
```

```bash
claude mcp add --transport http laminar https://api.lmnr.ai/v1/mcp \
  --header "Authorization: Bearer $LMNR_PROJECT_API_KEY"
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/laminar

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Arize Phoenix | BB | 75.6 | obs.traces, obs.evals, obs.datasets | https://www.anchorterminal.com/tools/arize-phoenix.min.md |
| Langfuse API + MCP | BB | 72.8 | obs.traces, obs.evals, obs.datasets | https://www.anchorterminal.com/tools/langfuse.min.md |
| LangSmith API + MCP | BB | 71.3 | obs.traces, obs.evals, obs.datasets | https://www.anchorterminal.com/tools/langsmith.min.md |
| Respan API + MCP | B | 65.9 | obs.traces, obs.evals, obs.datasets | https://www.anchorterminal.com/tools/respan.min.md |
| Braintrust API + MCP | C | 61.3 | obs.traces, obs.evals, obs.datasets | https://www.anchorterminal.com/tools/braintrust.min.md |


## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ Weekly SDKs, and a domain move nobody dated (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★★☆ Descriptions that say what to call first (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial)