← Back to search

io.github.mdfifty50-boop/qc-validator

mdfifty50-boop Scanned 3d ago

MCP server for runtime quality validation of AI agent outputs — hallucination detection, scope compl

MCP Registry ↗
B
81.1 / 100

Versions

0.1.0latest
first seen Jun 5, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 6

validate_output
annotations: none low

Score agent output quality against configurable criteria. Checks length, required keywords, forbidden patterns, claim density, and task relevance.

output string max_length number task_description string factual_claims_count number
check_hallucination_risk
annotations: none low

Estimate hallucination likelihood in agent output. If source text is provided, checks grounding. Otherwise flags outputs with high counts of specific numbers, dates, and URLs.

output string claim_count number source_text string
check_scope_compliance
annotations: none low

Validate that agent output stays within a defined scope contract. Checks allowed/forbidden topics, word limits, and required sections.

output string max_words number
log_validation
annotations: none low

Store a validation result for trending and failure pattern analysis. Accumulates per-agent statistics over time.

pass boolean score number agent_id string output_hash string issues_count number
get_failure_patterns
annotations: none low

Analyze common failure modes for a specific agent. Returns pass rate, average score, most frequent issue types, and quality trend direction.

agent_id string
generate_quality_report
annotations: none low

Generate a quality dashboard for all validated agents. Shows per-agent summaries, overall pass rate, worst/best performers, and actionable recommendations.

Permissions 1

env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 27

low
Tool 'validate_output' has no annotations annotation_checker · 100%
low
Tool 'check_hallucination_risk' has no annotations annotation_checker · 100%
low
Tool 'check_scope_compliance' has no annotations annotation_checker · 100%
low
Tool 'log_validation' has no annotations annotation_checker · 100%
low
Tool 'get_failure_patterns' has no annotations annotation_checker · 100%
low
Tool 'generate_quality_report' has no annotations annotation_checker · 100%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.12.0 (GHSA-345p-7cg4-v4c7) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.12.0 (GHSA-46jr-4wx8-v453) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.12.0 (GHSA-6prh-2h8m-c8cw) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.12.0 (GHSA-6qxp-vccf-f47h) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.12.0 (GHSA-8r9q-7v3j-jr4g) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.12.0 (GHSA-rvq5-wwqv-78pq) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.12.0 (GHSA-w48q-cv73-mx4w) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
Tool: validate_output manifest_parser · 70%
info
Tool: check_hallucination_risk manifest_parser · 70%
info
Tool: check_scope_compliance manifest_parser · 70%
info
Tool: log_validation manifest_parser · 70%
info
Tool: get_failure_patterns manifest_parser · 70%
info
Tool: generate_quality_report manifest_parser · 70%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (2) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 128 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%