evals-mcp-server

Purpose: Creating reproducible, reviewable AI evaluation datasets and exporting them into multiple evaluation formats.

Inferred · not functionally tested

Audience: AI evaluation engineers and developers

Inferred · not functionally tested

Functions: data_extraction, workflow_automation

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: Open Source · platforms: WEB · deployment: browser, cli, api_only, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: github.com. These links do not verify the individual claims.

In the Agent evaluation & testing space, evals-mcp-server takes a focused approach. Inferred · not functionally tested: It focuses on creating reproducible, reviewable AI evaluation datasets and exporting them into multiple evaluation formats. Inferred · not functionally tested: evals-mcp-server is an open-source project aimed at AI evaluation engineers and developers. Basis unknown · not verified: The project is open source (Open Source). Basis unknown · not verified: It runs on the web, the command line, and API, and it can be self-hosted.

cyanheads builds and maintains evals-mcp-server. Inferred · not functionally tested: Among its 6 catalogued features are draft workflows, review workflows, and revision workflows. Inferred · not functionally tested: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.