← Back to changelog

July 7, 2026

Query experiments via API and MCP

Tobias Wochinger

Fetch experiments and their items programmatically through the new public API endpoints, or let AI agents explore experiment results via the Langfuse MCP server.

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