MCP Tools DirectoryAbout this integration
MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations
- Transport
- stdio
- Authentication
- unknown
- Initial setup
- unknown
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.3.20
- Package
- mcp-as-a-judge
- Last compatibility test
- Not independently tested
Connect your agent
mcp-as-a-judgeQualified from complete pinned publisher README and manifest captures. The package and integration were not executed, installed, or independently security-audited.
Capabilities: plan evaluation, code review, test evaluation, MCP sampling
Connected profiles
Additional details
io.github.OtherVibes/mcp-as-a-judge
Source ↗ · Checked 2026-09-170.3.20
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17mcp-as-a-judge
Source ↗ · Checked 2026-09-190.5.0
Source ↗ · Checked 2026-09-19Publisher documentation provides a package launch command or MCP client process configuration; it was not executed in this isolated review.
Source ↗ · Checked 2026-09-19Authentication depends on the MCP host: supported sampling needs no API key, while other clients require a model-provider API key.
Source ↗ · Checked 2026-09-19The pinned README documents an MCP client configuration or a stdio connection for the reviewed packaged process.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19