Alfred VoC Analysis MCP v0.1

An MCP server that transforms Heum Alfred/DESK VoC facts into CX intelligence. The structure is explicitly separated into Fact → Analysis → Synthesis.

Architecture

• fact.py: FactRepository to be implemented by DB/API adapters; Facts do not store AI interpretation.

• analysis.py: computes overview, issue intelligence, CX concern, emerging signal, trend driver, and resolution effect in deterministic Python.

• synthesis.py: assembles the detailed Report, Executive Brief, and improvement Planning Signal DTO.

• server.py: FastMCP tool adapter. The analysis core does not depend on MCP or an external LLM.

The input schema preserves source extension fields with FactRecord(extra="allow"). It does not change the actual DB schema; production DB/API connections are added via the FactRepository adapter.

Related MCP server: NPS Chatbot MCP Server

MCP tools

• get_voc_overview

• analyze_issue_frequency, analyze_issue_severity, analyze_issue_persistence

• analyze_unresolved_issues, rerank_issue_priorities, compare_issue_portfolio

• analyze_customer_experience

• detect_emerging_signals

• analyze_voc_trends

• analyze_resolution_effect

• build_report_dataset, build_executive_brief, build_improvement_signals

Issue tools intentionally share one portfolio assessment so Frequency alone cannot contradict Priority Movement. Each issue result returns evidence, reason and confidence.

Run

python -m venv .venv
pip install -e ".[dev]"
pytest
alfred-voc-analysis-mcp

v0.1 ships an in-memory reference adapter. Embed the service and call configure_records, or implement FactRepository for voc-management DB/API.

Calibration

AnalysisConfig contains data-sufficiency and observation-window settings. Defaults are conservative technical defaults, not Heum policy. No opaque weighted score or fixed “N건=High” business rule is used.