Qc Validator

io.github.mdfifty50-boopPublished by GitHub account mdfifty50-boopv0.1.3Updated Oct 24, 2026

Output quality control and validation for AI agents

VerifiedSTDIODesktop onlyAI & ML

Overview

AI-generated overview

Local MCP server for quality control of AI agent output: scoring, hallucination-risk checks and scope compliance.

What you can do
Score agent output against configurable criteria (length limits, required keywords, forbidden patterns, factual claim density) and return issues and a recommendation. Estimate hallucination risk, checking sentence-level grounding when source text is given or flagging outputs dense with numbers, dates and URLs when it is not. Check output against a scope contract of allowed and forbidden topics, word limits and required sections. Log validation results and analyze pass rate, average score, common issues and trend per agent. Produce a quality dashboard report across all validated agents, also exposed as a resource.
When to use it
Use it when you want an automated check on agent output, such as length limits, required keywords, forbidden patterns, grounding against source text, or pass rates and recurring issues per agent.
Requirements
Runs locally with Node.js via npx from the npm package qc-validator-mcp over stdio; no configuration, account or API key needed. Desktop only.
Before you install
Validation results and statistics are kept in memory and are lost on restart, so they are not a durable audit log. The tools receive agent output and optional source text; make sure that content holds no confidential data you would not want processed.

Installation

In SourceWeft

  1. Open Qc Validator in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

qc-validator-mcp

Runtime quality validation for AI agent outputs. Detect hallucinations, enforce scope compliance, and score output quality — all via MCP.

Install

bash
npx qc-validator-mcp

Claude Desktop

json
{  "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_countReturns: { logged, agent_id, total_validations }

get_failure_patterns

Analyze common failure modes for a specific agent.

Params: agent_idReturns: { 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

Source: README.md at commit fac0ca0

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.3LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.