Judges Panel MCP server
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
7 stars164 downloads/wk
Reviews
Write oneNobody has reviewed Judges Panel yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Judges Panel tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
evaluate-codeEvaluate a code snippet or file for issues across all judge categories
evaluate-diffEvaluate a code diff (PR or commit) for introduced issues
review-projectFull project-level review with cross-file analysis
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan1500 source files scanned3/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 97 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (3)
- mediumeval / new Function used
exec.evaldist/api.js: … const result = evaluateCode("const x = eval(input);", "typescript"); * ``` */ // ─… - highShell command built from a string (injection risk)
exec.shell-concatdist/commands/auto-fix.js: …d separate arguments", before: 'exec("git " + command)', after: 'execFile("gi… - mediumsubprocess with shell=True
exec.shell-truedist/commands/benchmark-advanced.js: …ctory], capture_output=True, text=True, shell=True) return result.stdout.strip().split…
How Judges Panel compares
Against every graded Security MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 48/100
- higher than 8% of 915 Security servers
- Tools
- 3
- the typical Security server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 7
- more than 88% of 587 Security servers
- Downloads a week
- 164
- more than 72% of 248 Security servers with a package
What its tools let an agent do: 1 read · 2 run or deploy
Install Judges Panel in Claude Code, Cursor or VS Code
Runs npx -y @kevinrabun/judges on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add judges -- npx -y @kevinrabun/judges
Judges Panel: common questions
- Is Judges Panel MCP server safe?
- Not recommended: it is graded D (48/100). Read the Judges Panel safety report
- How do I install Judges Panel?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Judges Panel need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Judges Panel maintained?
- The last commit was 135 days ago (2026-06-22). The latest release is v3.129.9.
- What can I use instead of Judges Panel?
- Servers from other publishers that do the same job: Skylos MCP server, CodeInspectus MCP server and SonarQube MCP Server.
- How does Judges Panel compare with other Security MCP servers?
- safety score 48/100 (higher than 8% of 915 Security servers); tools 3 (the typical Security server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Judges Panel
Same job from other publishers: the closest match first, then the best rated.
- SkylosDead code, security, secrets detection and code quality for Python, TypeScript, Go.not reviewedEstablishedC
- CodeInspectusLocal-first MCP security scanner and CLI for AI-generated applications.not reviewedEstablishedC
- SonarQube MCP ServerAnalyze code quality and security with SonarQube Server or Cloud directly in AI assistants.not reviewedGrowingB
- Mastyf AIRuntime proxy for MCP security, cost governance & auditnot reviewedGrowingB
- SnykEasily find and fix security issues in your applications leveraging Snyk platform capabilities.not reviewedEstablishedB
