nexus-convergence-mcp
# nexus-convergence-mcp
MCP server wrapping the [Balanced Intelligence Convergence Pipeline](https://github.com/Gonzih/nexus-protocols).
Exposes the full pipeline as 4 MCP tools usable by any MCP-compatible client (Claude Code, Claude Desktop, etc.).
## Tools
### `converge_query`
Fan out a query to multiple LLMs, run consensus, return structured result.
```json
{
"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_ladder`
Return the full Evidence Ladder for a query — immutable audit trail of every pipeline step.
```json
{ "query_id": "run-uuid" }
```
Returns: ordered list of entries from `QUERY` → `DECOMPOSE` → `MODEL_EXECUTE` → `CONSENSUS` → `VERIFY` → `CONCLUDE`.
### `check_compliance`
Check content against HIPAA/EU_AI_ACT/NIST/CUSTOM policies.
```json
{
"content": "Patient SSN is 123-45-6789",
"categories": ["HIPAA"]
}
```
Returns: `passed`, `blocked`, `violations`, `warnings`, `logs`.
### `list_model_disagreements`
Return where models diverged — inversions (direct contradictions), disputed claims, low-similarity pairs.
```json
{ "query_id": "run-uuid" }
```
Returns: `inversions`, `disputed_claims`, `low_similarity_pairs`.
## MCP configuration
Add to your MCP config:
```json
{
"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"
}
}
}
}
```
## Environment
```bash
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
```
## Development
```bash
npm ci
npm run build
npm start
npm test
```
TDQS
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.