Evaluation report

• Repository is reachable

  https://github.com/ratel-ai/ratel @ cce540d — ★ 415 · Rust · MIT · last push 2 days ago

• Manifest detected

  kind=mcp slug=ratel-ai · path=src/sdk/python · source=pyproject.toml

• Slug is URL-safe

  "ratel-ai" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/ratel-ai

• Version is semver

  0.7.0

• Manifest present and parseable

  Manifest found at pyproject.toml.

• Name declared and well-formed

  Name "ratel-ai" is well-formed.

• Version is semver

  Version 0.7.0.

• Homepage or repository declaredwarn

  No homepage or repository declared.

  Add a "homepage" or "repository" field to pyproject.toml.

• Description quality

  19 words · 138 chars — "Python SDK for Ratel — context engineering platform for AI agents. BM25 tool ret…"

• README is present and substantial

  7,487 chars · 9 sections · 6 code blocks

• Tags / topics declared

  16 total — accuracy, agents, claude-skills, context, harness, llm (+10)

• README has usage / example sections

  found: Quickstart

• Homepage / docs URL declared

  https://www.ratel.sh/

• LICENSE file at repo root

  LICENSE.md

• No sensitive files in the repo

  scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

• No dependencies that impersonate popular packages

  39 dependencies, none impersonating a popular package.

• License declared

  License file present.

• No credentials assembled from parts

  No assembled credentials in 10 files.

• MCP: launch path

  launch declared in pyproject.toml

• MCP: @modelcontextprotocol/sdk in dependencies

  non-Node server (pyproject.toml) — uses its language's MCP SDK

• MCP: ESM package

  non-Node server (pyproject.toml) — n/a

• MCP: server surface

  0 tools

• Recent activity

  last push 2 days ago

• Tests detected

  6 test directories · 54 test files

• CI configuration detected

  GitHub Actions (8 workflows)

• Maintenance activity · queued

  No commit timestamp available for this source.

This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.