Skip to main content
Glama
nexus-convergence-mcp

nexus-convergence-mcp

by Gonzih

nexus-convergence-mcp

Balanced Intelligence Convergence Pipeline을 래핑하는 MCP 서버입니다.

전체 파이프라인을 모든 MCP 호환 클라이언트(Claude Code, Claude Desktop 등)에서 사용할 수 있는 4개의 MCP 도구로 노출합니다.

도구

converge_query

쿼리를 여러 LLM으로 팬아웃하고, 합의를 실행하며, 구조화된 결과를 반환합니다.

{
  "query": "Is this treatment effective?",
  "models": ["gpt-4o", "claude-3-5-sonnet-20241022", "gemini-1.5-pro"],
  "policy_set": "hipaa"
}

반환값: run_id, agreement_score, stability, agreed_claims, disputed_claims, final_answer.

get_evidence_ladder

쿼리에 대한 전체 증거 사다리(Evidence Ladder)를 반환합니다 — 모든 파이프라인 단계의 변경 불가능한 감사 추적입니다.

{ "query_id": "run-uuid" }

반환값: QUERY → DECOMPOSE → MODEL_EXECUTE → CONSENSUS → VERIFY → CONCLUDE에서 항목의 순서가 지정된 목록.

check_compliance

HIPAA/EU_AI_ACT/NIST/CUSTOM 정책에 따라 콘텐츠를 확인합니다.

{
  "content": "Patient SSN is 123-45-6789",
  "categories": ["HIPAA"]
}

반환값: passed, blocked, violations, warnings, logs.

list_model_disagreements

모델이 어디에서 갈라졌는지 반환합니다 — 반전(직접적인 모순), 논쟁의 여지가 있는 주장, 낮은 유사성 쌍.

{ "query_id": "run-uuid" }

반환값: inversions, disputed_claims, low_similarity_pairs.

Related MCP server: agent-orchestrator

MCP 구성

MCP 구성에 추가하세요:

{
  "mcpServers": {
    "nexus-convergence": {
      "command": "npx",
      "args": ["-y", "@gonzih/nexus-convergence-mcp"],
      "env": {
        "CONVERGENCE_SERVICE_URL": "http://your-convergence-service:3000",
        "CONSENSUS_SERVICE_URL": "http://your-consensus-service:3001",
        "EVIDENCE_SERVICE_URL": "http://your-evidence-service:3002",
        "COMPLIANCE_SERVICE_URL": "http://your-compliance-service:3003",
        "NEXUS_API_KEY": "your-api-key"
      }
    }
  }
}

환경

CONVERGENCE_SERVICE_URL=http://localhost:3000
CONSENSUS_SERVICE_URL=http://localhost:3001
EVIDENCE_SERVICE_URL=http://localhost:3002
COMPLIANCE_SERVICE_URL=http://localhost:3003
NEXUS_API_KEY=your-api-key

개발

npm ci
npm run build
npm start
npm test

Available Tools

4 tools
check_complianceA

Check content against compliance policy sets. Evaluates against HIPAA (PHI detection), EU_AI_ACT (prohibited use cases), NIST (PII/secrets), and CUSTOM rules. Returns: passed/blocked status, list of violations (BLOCK), warnings (WARN), and log entries.

Inputs: content (required), categories.

converge_queryA

Fan out a query to multiple LLMs in parallel (OpenAI, Claude, Gemini, Ollama), run multi-stage consensus validation, and return a structured result with agreement score, truth stability classification, and provenance. NEVER rely on one model answer. Friction between disagreements = intelligence.

Inputs: query (required), models, policy_set.

get_evidence_ladderA

Return the full Evidence Ladder for a query — immutable append-only audit trail showing every step: QUERY → DECOMPOSE → MODEL_EXECUTE → CONSENSUS → VERIFY → CONCLUDE. Each entry records: step, actor (model name or "system"), content, confidence, and timestamp.

Inputs: query_id (required).

list_model_disagreementsA

Return where models diverged on a query — direct contradictions (inversions), disputed claims, and low-similarity pairs with their similarity scores. Use this to understand the friction space: inversions are not errors, they are intelligence.

Inputs: query_id (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: compliance checking, multi-model querying, audit trail retrieval, and disagreement analysis. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern in snake_case (check_compliance, converge_query, get_evidence_ladder, list_model_disagreements), making naming predictable and easy to understand.

    Tool Count3/5

    With only 4 tools, the server covers a narrow scope. While each tool is essential, the low count may leave agents wanting for configuration or management tools, but it is still reasonable for a focused server.

    Completeness2/5

    The domain of multi-model querying with compliance and audit lacks essential management operations such as listing available models, configuring compliance rules, or retrieving past query history. Significant gaps will cause agent failures.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables users to query, compare, and synthesize responses from multiple local and cloud LLMs simultaneously using existing subscriptions. It provides tools for parallel model evaluation, consensus polling with an LLM-as-judge, and response synthesis across different model providers.
      8
      59 npm
      15
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Exposes RAG and document intelligence pipelines as 8 composable tools for MCP-compatible clients, enabling querying, indexing, classifying, extracting, and assessing documents.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Audits decisions for cognitive biases through an adversarial framework, exposing tools like analyze_decision, list_biases, and get_bias via MCP.
      MIT