evaluate_focused

MCP tool from Judges by KevinRabun

Run only specified judges. Use after an initial full evaluation to re-check specific areas.

How to use it

evaluate_focused is exposed by the Judges MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the evaluate_focused tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Judges

$npx @kevinrabun/judges-cli eval --file src/app.ts

FULL JUDGES LISTING

Other tools in Judges (39)

string

number[]

string

string

string

boolean

evaluate_app_builder_flow

Run a 3-step app-builder workflow for technical and non-technical stakeholders:

evaluate_batch

Evaluate multiple code files in a single call. Returns per-file verdicts plus aggregate statistics.

evaluate_code_streaming

Streaming evaluation — returns per-judge results as each judge completes with running aggregates.

evaluate_file

Read a file from disk and submit it to the full panel. Auto-detects language from extension.

evaluate_policy_aware

Policy-aware evaluation with named profiles (startup, regulated, healthcare, fintech, public-sector).

evaluate_public_repo_report

Clone a public repository URL, run the full judges panel across eligible source files, and generate a consolidated markdown report.

evaluate_then_fix

Evaluate code and automatically generate fix patches for all findings with auto-fix support.

evaluate_v2

Run a V2 context-aware tribunal evaluation designed to raise feedback quality toward lead engineer/architect-level review:

evaluate_with_progress

Evaluate with progress callbacks for long-running evaluations.

evaluationContext

object

evidence

object

explain_finding

Explain a finding in plain language with OWASP/CWE references, risk context, and remediation guidance.

files

array

fix_code

Evaluate code and apply all available auto-fix patches. Returns fixed code with applied/remaining summary.

get_finding_stats

Finding lifecycle statistics: open, fixed, recurring, and triaged counts plus trends.

get_suppression_analytics

Analyze suppression patterns: FP rates by rule, suppression rates, auto-suppress candidates.

includeAstFindings

boolean

keepClone

boolean

language

string

list_triaged_findings

List triaged findings, optionally filtered by triage status.

number

number

number

number

number

number

mustFixDangerousRulePrefixes

string[]

number

string

enum

Record user feedback (true-positive, false-positive, wont-fix) to calibrate confidence scores.

repoUrl

string

triage_finding

Set triage status of a finding (accepted-risk, deferred, wont-fix, false-positive) with attribution.