Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@nexus-convergence-mcp converge query: Is this drug safe? Models: gpt-4o, claude-3, gemini"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server wrapping the Balanced Intelligence Convergence Pipeline.
Exposes the full pipeline as 4 MCP tools usable by any MCP-compatible client (Claude Code, Claude Desktop, etc.).
converge_queryFan out a query to multiple LLMs, run consensus, return structured result.
{
"query": "Is this treatment effective?",
"models": ["gpt-4o", "claude-3-5-sonnet-20241022", "gemini-1.5-pro"],
"policy_set": "hipaa"
}Returns: run_id, agreement_score, stability, agreed_claims, disputed_claims, final_answer.
get_evidence_ladderReturn the full Evidence Ladder for a query — immutable audit trail of every pipeline step.
{ "query_id": "run-uuid" }Returns: ordered list of entries from QUERY → DECOMPOSE → MODEL_EXECUTE → CONSENSUS → VERIFY → CONCLUDE.
check_complianceCheck content against HIPAA/EU_AI_ACT/NIST/CUSTOM policies.
{
"content": "Patient SSN is 123-45-6789",
"categories": ["HIPAA"]
}Returns: passed, blocked, violations, warnings, logs.
list_model_disagreementsReturn where models diverged — inversions (direct contradictions), disputed claims, low-similarity pairs.
{ "query_id": "run-uuid" }Returns: inversions, disputed_claims, low_similarity_pairs.
Related MCP server: agent-orchestrator
Add to your MCP config:
{
"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"
}
}
}
}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-keynpm ci
npm run build
npm start
npm testCheck 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.
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.
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).
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).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
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.
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.
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.
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.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
MCP gateway: one connection for your AI apps, with tool policies, PII redaction and audit logs.
