Evaluation report

• Repository is reachable

  https://github.com/Mintplex-Labs/anything-llm @ 8597349 — ★ 61,864 · JavaScript · MIT · last push 2 days ago

• Manifest detected

  kind=mcp slug=anything-llm-server · path=server · source=package.json

• Slug is URL-safe

  "anything-llm-server" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/anything-llm-server

• Version is semver

  1.14.1

• README has usage / example sectionswarn

  README has no Usage / Example / Quick start / Installation heading at any level

  Add a `# Usage`, `## Quick start`, or similar section so end users can copy/paste a working invocation. Code blocks alone work too if there are several.

• Description quality

  9 words · 58 chars — OK but more detail helps

• README is present and substantial

  25,596 chars · 8 sections

• Tags / topics declared

  13 total — agent-harness, agentic-ai, ai-agents, hermes-agent, llm, local-ai (+7)

• Homepage / docs URL declared

  https://anythingllm.com

• Dependencies: known vulnerabilitieswarn

  3 high/critical advisories — @langchain/[email protected] (HIGH: GHSA-r399-636x-v7f6) · @modelcontextprotocol/[email protected] (HIGH: GHSA-345p-7cg4-v4c7) (+1)

  Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)

• LICENSE file at repo root

  LICENSE

• No sensitive files in the repo

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

• MCP: ESM packagewarn

  package.json missing "type": "module"

  Modern MCP servers are ESM. Add `"type": "module"` unless you have a CJS-only reason.

• MCP: launch path

  scripts.start

• MCP: @modelcontextprotocol/sdk in dependencies

  pinned at "^1.24.3"

• MCP: SDK version pinned

  pinned at "^1.24.3"

• MCP: server surface

  0 tools

• Recent activity

  last push 2 days ago

• Tests detected

  1 test directory · 23 test files

• CI configuration detected

  GitHub Actions (9 workflows)

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.