MCP As A Judge
MCP as a Judge is a behavioral MCP that strengthens AI coding assistants by requiring explicit LLM evaluations
Is MCP As A Judge safe? Thin or incomplete trust evidence. Review carefully before production use.
Compare MCP As A Judge
How does it stack up against its MCP Servers neighbours?
Pick any agent to compare →In detail: MCP As A Judge scores 36.1/100 (Grade D), ranked #1279 of 1378 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 2.8/10; 13% of recent commits are signed; no published advisory affects its latest release (mcp-as-a-judge); last pushed 2025-12-15. Every point is earned from checkable signals — never paid placement. How scoring works →
How MCP As A Judge could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Publish build provenance for its packagesPyPI Trusted Publishing attestations +14.7 → 50.8 C · #554 of 781
- Raise the OSSF Scorecard from 2.8 to 9.0lowest checks: CII-Best-Practices 0, Code-Review 0, Dangerous-Workflow 0 +13.0 → 49.1 D · #585 of 781
- Sign every commit13% signed today +4.4 → 40.5 D · #693 of 781
Chain of custody
Scanners check what the code says. This traces who ships MCP As A Judge and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/OtherVibes/mcp-as-a-judge, MIT, last pushed 2025-12-15. 13% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Weak
OpenSSF Scorecard rates the repository's practices 2.8/10 (scanned Oct 15, 2026). The checks that decide who can get a change released:
- Code Review0
- Branch Protection5
- Signed Releases0
- Dangerous Workflow0
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 5CI-Tests 10CII-Best-Practices 0Code-Review 0Contributors 3Dangerous-Workflow 0Dependency-Update-Tool 10Fuzzing 0License 10Maintained 0Packaging 10Pinned-Dependencies 0SAST 0Security-Policy 0Signed-Releases 0Token-Permissions 0Vulnerabilities 0 -
Published packages Linked, not attested
- PyPI mcp-as-a-judge Source link points back to this repo No build attestation
Without a build attestation, nothing proves the published files were built from this repository.
-
What you install today No known advisories
Latest release checked: mcp-as-a-judge 0.5.0. No published advisory affects it (OSV, checked 2026-10-18).
Changes to this chain
- 2026-09-02 OSSF Scorecard: 2.8/10
Evidence behind this score
Coverage B: 3 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues MCP As A Judge’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How MCP As A Judge compares in MCP Servers
- #736 Bigquery MCP 36.2 +0.1
- #737 Carbon Arc 36.2 +0.1
- #738 MCP As A Judge 36.1 this agent
- #739 Aigroup Mdtoword MCP 36.1 ±0
- #740 Agent MCP Gateway 35.9 −0.2
Bars show each HVTrust score; the tick marks MCP As A Judge’s 36.1.
Where the 36.1 comes from
HVTrust dimensions vs the MCP Servers average
36.1 / 100 · 100.0% confidenceMCP As A Judge MCP Servers average (781 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade D reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
12.2 / 100Common questions about MCP As A Judge
Does MCP As A Judge publish package provenance?
Does MCP As A Judge have an OpenSSF Scorecard?
Is MCP As A Judge actively maintained?
What license does MCP As A Judge use?
Are MCP As A Judge's commits signed?
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
AI agent surface
MCP, providers, tool surface
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Detected changes to MCP As A Judge's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.
Maintain MCP As A Judge?
For maintainers
HVTrust scores MCP As A Judge from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/mcp-as-a-judge)
<a href="https://hvtracker.net/agents/mcp-as-a-judge"><img src="https://hvtracker.net/badge/mcp-as-a-judge.svg" alt="HVTrust"></a>
Other agents in MCP Servers
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON