MCP Radar
MCP-Server

llm-output-quality-monitor

io.github.lazymac2x/llm-output-quality-monitor
KI & Agenten Entwicklertools Öffentlich und erreichbar MCP 2026-07-28

Was dieses MCP kann

Checks LLM responses for consistency, quality, schema compliance, drift, and heuristic hallucination risk.

Funktionen

Tools

5 Tools
consistency_check
Check consistency across multiple LLM responses
Eingabeschema 
{'type': 'object', 'required': ['responses'], 'properties': {'responses': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Array of responses to compare'}}}
drift_detector
Detect quality drift between current and previous LLM responses
Eingabeschema 
{'type': 'object', 'required': ['currentResponse', 'previousResponse'], 'properties': {'threshold': {'type': 'number', 'description': 'Drift threshold (0-1, default: 0.15)'}, 'currentResponse': {'type': 'string', 'description': 'Current LLM response'}, 'previousResponse': {'type': 'string', 'description': 'Previous LLM response'}}}
hallucination_scorer
Pattern-based heuristic risk scoring for LLM responses (0-100). Detects linguistic signals such as contradictory assertions, unsourced claims, and uncertainty markers. Not a semantic hallucination detector.
Eingabeschema 
{'type': 'object', 'required': ['response'], 'properties': {'context': {'type': 'string', 'description': 'Reference context for grounding'}, 'response': {'type': 'string', 'description': 'LLM response to analyze'}}}
quality_validator
Validate LLM response quality based on length, format, and structure
Eingabeschema 
{'type': 'object', 'required': ['response'], 'properties': {'response': {'type': 'string', 'description': 'LLM response to validate'}, 'maxLength': {'type': 'number', 'description': 'Maximum response length (default: 10000)'}, 'minLength': {'type': 'number', 'description': 'Minimum response length (default: 10)'}, 'strictFormat': {'type': 'boolean', 'description': 'Enforce punctuation and capitalization'}}}
schema_enforcer
Validate JSON response against schema
Eingabeschema 
{'type': 'object', 'required': ['response', 'schema'], 'properties': {'schema': {'type': 'object', 'description': 'JSON schema definition'}, 'response': {'type': 'string', 'description': 'JSON response to validate'}}}
Verlauf

Letzte Tool-Änderungen

Hinzugefügt
consistency_check
17. September 2026 12:43
Hinzugefügt
schema_enforcer
17. September 2026 12:43
Hinzugefügt
hallucination_scorer
17. September 2026 12:43
Hinzugefügt
drift_detector
17. September 2026 12:43
Hinzugefügt
quality_validator
17. September 2026 12:43
Entdecken

Ähnliche MCP-Server

Andreax

io.github.moralito311-andr/andreax

Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…

IA-QA — 130+ QA & Dev Tools for AI Agents

io.github.JcJamet/ia-qa-toolbox

Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…

CompletionKit

com.completionkit/evals

Runs prompt evaluation workflows over datasets using deterministic checks and LLM judges, with metrics, scoring runs, agreements,…

Replicate

io.github.pipeworx-io/replicate

Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…

Huggingface

io.github.pipeworx-io/huggingface

Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.

Ai Model Experiments

io.github.pipeworx-io/ai-model-experiments

Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.

rubrkit

com.rubrkit/rubrkit

Manages AI evaluation artifacts, rubric audits, eval runs, golden cases, proof reports, and drift monitoring for LLM outputs.

Hipocampo MCP

io.github.carrasquelalex1/hipocampo

Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…