# Langfuse API + MCP (slim)

> Open-source tracing, evaluation, prompt management and datasets for LLM apps and agents, built on OpenTelemetry.

- Full: https://www.anchorterminal.com/tools/langfuse.md (~6,450 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/langfuse.json · canonical https://www.anchorterminal.com/tools/langfuse
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 72.8/100 · rank #66 of 452 · #2 in Agent observability & evals · agent-ready · confidence high**


Assessment: MIT core with no usage limits when self-hosted, and self-hosted telemetry documented with an off switch. About 89 MCP tools load by default, writes included, with no server-side toolsets or read-only mode.

## Facts

- Kind: HTTP API · vendor: Langfuse (ClickHouse) · category: Agent observability & evals · legal entity: Langfuse GmbH (a ClickHouse, Inc. company) · provenance 82/100
- Endpoint: `https://cloud.langfuse.com/api/public` (HTTP, Streamable HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: MIT (core), commercial licence for the ee directories
- Probe metrics: not measured yet (probes haven't run)
- Free tier: Hobby, 50,000 units a month, 30 days of data, 2 users, no card
- Rate limits: Ingestion 1,000 requests a minute on Hobby, 4,000 on Core, 20,000 on Pro, custom on Enterprise. Other APIs have separate per-organisation buckets and return 429 with Retry-After. 5 MB per request and per response
- What appears in a trace: Nested spans, generations with tokens and cost, tool calls, sessions, users and scores, from the SDKs or any OpenTelemetry exporter (vendor's description)
- Evaluations: Datasets, experiments via SDK or UI, LLM-as-a-judge and code evaluators, annotation queues. Experiments can be re-run against a fixed dataset version
- MCP server: Hosted at `/api/public/mcp` on every cloud region and self-hosted instance, streamable HTTP, Basic auth. Tools cover prompts, observations, metrics, scores, datasets, evaluators, dashboards and annotation queues. Read and write by default
- Data retention: 30 days on Hobby, 90 days on Core, 3 years on Pro and Enterprise, configurable retention policies on Pro and above
- Webhooks: Prompt change webhooks and Slack, project notification channels
- Open source: MIT core on GitHub, Docker Compose and a Helm chart. Enterprise add-ons sit in ee directories under a commercial licence
- Compliance: SOC 2 Type II and ISO 27001 reports and a HIPAA BAA on Pro and above (vendor's claim)
- Prices: Core plan $29 per month (plan); Pro plan $199 per month (plan); Enterprise plan $2499 per month (plan); Teams add-on $300 per month (plan)
- 2026-01-16 Notice: Acquired by ClickHouse. Open-source licence and cloud SLAs unchanged

- Scores: Reliability 80, Performance pending, Schema & documentation 93, Agent ergonomics 74, Security & auth 65, Payments & pricing 40, Task success pending, Maintenance & community 88, Transparency & trust 87 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, incident.io status page with five components (ingestion, prompts, UI, public API, LLM-as-a-judge) in each of the EU, US, HIPAA and JP region… · Schema & documentation, Public OpenAPI at cloud.langfuse.com, and every MCP tool takes a typed zod schema (25). · Agent ergonomics, About 89 MCP tool definitions in the source on 1 October, all enabled by default, with no server-side toolsets. · Security & auth, Project-scoped key pairs over Basic auth, revocable, with organisation keys kept to admin APIs. · Payments & pricing, No x402 or other machine payment (0). · Maintenance & community, Server v4.49.0 tagged on 2026-10-01 (30). · Transparency & trust, MIT core with the ee directories under a commercial licence (27).
- Sources: 12, open questions: 2, both in the full twin
- Capabilities: obs.traces, obs.evals, obs.prompts, obs.datasets
- JSON: https://www.anchorterminal.com/api/v1/tools/langfuse.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/langfuse.svg` or a link to https://www.anchorterminal.com/tools/langfuse from a page on langfuse.com or one of its subdomains, or the README of github.com/langfuse/langfuse, 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. Allowlist only the tools the agent needs. All 89 load by default and the write tools are among them
2. Ask `listObservations` for specific `fields`. Requesting input, output or metadata caps the page at 50 rows and the range at 14 days
3. Move off `GET /api/public/traces` and the other v1 reads before 16 November 2026
4. On 429, wait for `Retry-After`. MCP calls share the organisation's General API bucket
5. Pick the regional host (cloud, us.cloud, jp.cloud, hipaa.cloud) that matches the project's keys

## Connect

```bash
curl -u "$LANGFUSE_PUBLIC_KEY:$LANGFUSE_SECRET_KEY" https://cloud.langfuse.com/api/public/projects
```

```bash
claude mcp add --transport http langfuse https://cloud.langfuse.com/api/public/mcp \
  --header "Authorization: Basic $(printf '%s:%s' "$LANGFUSE_PUBLIC_KEY" "$LANGFUSE_SECRET_KEY" | base64)"
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/langfuse

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Arize Phoenix | BB | 75.6 | obs.traces, obs.evals, obs.prompts, obs.datasets | https://www.anchorterminal.com/tools/arize-phoenix.min.md |
| LangSmith API + MCP | BB | 71.3 | obs.traces, obs.evals, obs.prompts, obs.datasets | https://www.anchorterminal.com/tools/langsmith.min.md |
| Respan API + MCP | B | 65.9 | obs.traces, obs.evals, obs.prompts, obs.datasets | https://www.anchorterminal.com/tools/respan.min.md |
| Braintrust API + MCP | C | 61.3 | obs.traces, obs.evals, obs.prompts, obs.datasets | https://www.anchorterminal.com/tools/braintrust.min.md |
| HoneyHive | C | 55.9 | obs.traces, obs.evals, obs.prompts, obs.datasets | https://www.anchorterminal.com/tools/honeyhive.min.md |


## Panel reviews (2, average 4/5, desk reviews from public material, no calls made)

- ★★★★☆ Old read APIs end 16 November, and it says so (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★★☆ Practical descriptions, 89 of them (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial)