---
date: 2026-07-07
title: Query experiments via API and MCP
description: Fetch experiments and their items programmatically through the new public API endpoints, or let AI agents explore experiment results via the Langfuse MCP server.
author: Tobias Wochinger
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

You can now access experiment results programmatically. The new `GET /api/public/experiments` and `GET /api/public/experiment-items` endpoints list experiments and their items with cursor-based pagination. The Langfuse MCP server exposes them as `listExperiments` and `listExperimentItems` tools.

This unlocks workflows beyond the Langfuse UI:

- Analyze experiments from AI agents: agents can list recent experiments, drill into individual items, and follow the deep links in MCP responses back into Langfuse.
- Export experiment results: pull item inputs, outputs, expected outputs, and scores into a notebook or data warehouse for custom analysis.
- Gate deployments in CI/CD: fetch the scores of an experiment run and fail the pipeline if they regress.

```
GET /api/public/experiments?fromStartTime=2026-07-01T00:00:00Z&fields=core,scores
GET /api/public/experiment-items?fromStartTime=2026-07-01T00:00:00Z&experimentId=exp-123&fields=io,scores
```

## Get started

- [Experiments documentation](/docs/evaluation/experiments/experiments-via-sdk)
- [API reference](https://api.reference.langfuse.com/#tag/experiments)
- [MCP server documentation](/docs/api-and-data-platform/features/mcp-server)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2026-07-07-experiments-public-api-and-mcp.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.