About qc-validator
qc-validator is an MCP server for checking AI agent outputs at runtime. It scores configurable quality criteria, estimates hallucination risk, checks scope compliance, and tracks validation results by agent.
Key features
- 01Score outputs against configurable criteria
- 02Estimate hallucination risk
- 03Check scope and format requirements
- 04Log per-agent validation results
- 05Analyze failure patterns and trends
- 06Generate cross-agent quality reports
Use cases
- 01Review agent output against task criteria
- 02Check claims against supplied source text
- 03Enforce topic and section boundaries
- 04Track agent quality over time
MCP support
It exposes output validation, risk checks, logging, and reporting tools to MCP clients, along with a dashboard resource containing quality metrics.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| output | string | Yes | The agent output text to validate |
| criteria | object | Yes | Quality criteria to check against |
| criteria.max_length | number | No | Maximum character length for the output |
| criteria.required_keywords | array | No | Keywords that must appear in the output |
| criteria.forbidden_patterns | array | No | Regex patterns or strings that must NOT appear |
| criteria.factual_claims_count | number | No | Maximum number of factual claims before flagging high density |
| task_description | string | Yes | Description of what the agent was asked to do |
Details
From the project READMEqc-validator-mcp
Runtime quality validation for AI agent outputs. Detect hallucinations, enforce scope compliance, and score output quality — all via MCP.
Install
npx qc-validator-mcp
Claude Desktop
{
"mcpServers": {
"qc-validator": {
"command": "npx",
"args": ["qc-validator-mcp"]
}
}
}
Tools
validate_output
Score agent output against configurable criteria: length limits, required keywords, forbidden patterns, and factual claim density.
Params: output, task_description, criteria { max_length, required_keywords[], forbidden_patterns[], factual_claims_count }
Returns: { pass, score, issues[], recommendation }
check_hallucination_risk
Estimate hallucination likelihood. With source text, checks sentence-level grounding. Without source, flags outputs dense with specific numbers, dates, and URLs.
Params: output, source_text (optional), claim_count (default 5)
Returns: { risk_level, unsupported_claims[], confidence, suggestion }
check_scope_compliance
Validate output against a scope contract — allowed/forbidden topics, word limits, required sections.
Params: output, scope { allowed_topics[], forbidden_topics[], max_words, required_sections[] }
Returns: { compliant, violations[], scope_utilization_percent }
log_validation
Store validation results for per-agent trending.
Params: agent_id, output_hash, score, pass, issues_count
Returns: { logged, agent_id, total_validations }
get_failure_patterns
Analyze common failure modes for a specific agent.
Params: agent_id
Returns: { total_validations, pass_rate, avg_score, most_common_issues[], trend }
generate_quality_report
Quality dashboard across all validated agents — no parameters required.
Returns: { total_agents, overall_pass_rate, agents[], worst_performers[], best_performers[], recommendations[] }
Resource
qc://dashboard— Quality metrics for all validated agents
Architecture
- Pure Node.js ES modules
- In-memory Maps (no external dependencies)
- stdio transport via @modelcontextprotocol/sdk
- Zero configuration required
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.