unmerged-approaches-mcp
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., "@unmerged-approaches-mcp Consult 5 models: 'Should we switch to Kubernetes?'"
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.
unmerged-approaches-mcp
An MCP server that puts one identical brief to several LLMs in parallel and hands back every answer verbatim — unmerged, unranked, unsynthesized.
Most multi-model MCP servers end in a judge, a synthesizer, or a consensus loop. This one deliberately does not. The moment N answers are averaged into one confident paragraph, the single most useful piece of information is destroyed: whether the models actually agreed.
Four models independently reaching the same conclusion is corroboration.
Two against two is a real open question your one-model answer would have hidden from you.
A synthesizer renders both of those as the same smooth prose. This server refuses to, by design.
What it does
Fans one brief out to up to 12 OpenRouter models concurrently — 400+ models, one API key.
Returns per-model: the verbatim answer,
finish_reason, latency, token usage, cost, and a structured error when a model fails.A slow or failing model becomes one failed entry; it never sinks the panel.
Persists bounded, redacted, correlation-ID-addressable debug events.
Never merges, ranks, scores, votes on, or picks a winner among the answers.
Related MCP server: Legion MCP Server
Install
stdio (Claude Desktop, Claude Code, Cursor, Cline, Zed)
{
"mcpServers": {
"unmerged-approaches": {
"command": "npx",
"args": ["-y", "unmerged-approaches-mcp@latest"],
"env": { "OPENROUTER_API_KEY": "sk-or-v1-..." }
}
}
}claude mcp add unmerged-approaches npx -y unmerged-approaches-mcpRemote Streamable HTTP
OPENROUTER_API_KEY=sk-or-v1-... UNMERGED_AUTH_TOKEN=your-token npx unmerged-approaches-mcp-http
# or: node src/http.jsMounts MCP at /mcp and a separate liveness probe at /health.
{
"mcpServers": {
"unmerged-approaches": {
"type": "http",
"url": "https://your-host.example/mcp"
}
}
}Send the token as Authorization: Bearer <token> or x-api-key. Keep secrets in your client's secret storage, never in a committed config file.
Tools
Tool | Category | What it does |
| PANEL | One brief → N models in parallel → N verbatim answers, unmerged |
| SYSTEM | Live OpenRouter catalog: substring search, free-only filter, cursor pagination |
| SYSTEM | Server version, credential validity, remaining credit, default panel, limits |
| DEBUG | Newest-first structured events, filterable by correlationId / level / event / operation / time |
All four are read-only and non-destructive. The server exposes no arbitrary HTTP, shell, or SQL primitive.
consult
Argument | Type | Notes |
| string, required | Sent byte-for-byte identically to every model. Max 200,000 chars. |
| string[] | Exact OpenRouter ids, max 12, deduplicated. Omit for the default panel. |
| string | Optional system prompt, identical for every model. |
| int | Default 8000, ceiling 32000. |
| number | 0–2, default 0.7. |
| int | Default 180000, max 600000. Per model, not for the batch. |
Returns correlationId, requestedModels, answeredCount, completeCount, failedCount, totalCostUsd, wallClockMs, and answers[] with { model, actualModel, ok, complete, finishReason, content, error, latencyMs, usage }.
If every model fails, the call returns isError: true with code ALL_MODELS_FAILED. A partial panel is a success.
Writing a brief that is worth the money
The output is only as good as the isolation of the input. A brief that leaks your preferred answer gets it echoed back by every model, and you will mistake that echo for agreement.
Include the goal, hard constraints, what is already decided, what was rejected and why, and what is genuinely unknown.
Mark unverified claims as unverified. Distinguish what you observed from what you assumed.
Do not name your preferred option, and do not tell the panel what an earlier model said.
Ask for independent judgment, not novelty.
Environment variables
Name | Required | Purpose |
| yes | OpenRouter credential. Server-side only; never accepted as a tool argument. |
| no | Comma-separated default panel. |
| no | Panel size cap. Default 12. |
| no | Default output ceiling per model. Default 8000. |
| no | Default per-model timeout. Default 180000. |
| no | Retained debug events. Default 500. |
| http only | Bearer / |
| http only | Comma-separated browser origin allowlist. Browsers are refused unless listed. |
| http only | Defaults |
No value is ever written to logs, tool results, or client configuration.
Cost
You pay per model, per call. A 5-model panel is roughly 5× a single call. list_models with free_only: true finds zero-price models; free endpoints time out and rate-limit far more often, which shows up honestly in failedCount.
Security
Credentials are read only from the server environment and are never accepted as tool arguments.
Anything credential-shaped is stripped from errors and debug events before persistence.
The HTTP transport validates
Origin, requires a bearer token when one is configured, and compares it in constant time.Returned answers are untrusted third-party model output. If an agent calls this on attacker-influenced input, treat the answers as data to weigh, never as instructions to execute. This is a prompt-injection surface like any MCP tool that returns external content.
Development
npm install
npm run build # syntax check every entrypoint
npm test # 9 contract tests incl. a live stdio initialize/list/call handshakeLicense
MIT
Available Tools
4 toolsconsultConsult an unmerged panel of modelsARead-only
Send ONE identical brief to several LLMs in parallel and get every answer back verbatim, attributed, unranked and unsynthesized. Use when a decision is consequential or hard to reverse, when you want your own reasoning stress-tested by models that did not see it, or when the user asks for other opinions or approaches. The value is the spread: independent agreement is corroboration, a split is a real open question that a single answer would have hidden from you. This server never merges, ranks or picks a winner.
Inputs: brief (required), models, system, max_tokens, +2 more.
get_debug_logsRead persisted structured debug eventsARead-onlyIdempotent
Newest-first structured events for dispatches, per-model failures and validation errors, filterable by correlationId, level, event, operation and time, with cursor pagination. Every consult result carries a correlationId: pass it here to see exactly what happened per model. Credentials are redacted before persistence.
Inputs: event, level, limit, since, +3 more.
get_statusServer, credential and limit statusARead-onlyIdempotent
Report server version, whether OPENROUTER_API_KEY is configured and accepted, remaining credit, the default panel and the configured limits. Call this first when consult fails with an authentication error. Never returns the key itself.
Inputs: no named parameters.
list_modelsList available OpenRouter modelsARead-onlyIdempotent
Browse the live OpenRouter model catalog to pick an exact panel for consult. Supports substring search, a free-only filter and cursor pagination. Model ids change over time, so resolve them here rather than guessing.
Inputs: sort, limit, query, cursor, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct role: consult is the core action, list_models handles model selection, get_status handles configuration/health checks, and get_debug_logs is for diagnostics. There is no meaningful overlap or possible confusion between the tool boundaries.
get_status, list_models, and get_debug_logs all follow a clean lower_snake verb_noun pattern. consult is a bare verb without an explicit object, which is a minor deviation, but it still reads naturally and fits the overall imperative style.
Four tools is well-scoped for a narrow server: one primary operation plus three supporting utilities for configuration, model discovery, and debugging. Every tool earns its place and there is no redundancy.
The domain is parallel unmerged consultation, and consult fully covers the core workflow while list_models, get_status, and get_debug_logs cover the supporting needs around model selection, auth/config validation, and failure investigation. There are no obvious dead ends or missing operations agents would need.
Related MCP Connectors
Ask GPT, Claude, Gemini and Grok at once: one consensus answer plus where they agree and split.
Fan out deep research across multiple AI providers, synthesize into one unified report.
Answers, sources and brand mentions from OpenAI, Perplexity, Gemini, Claude and Grok side by side.
A second opinion for AI agents: one prompt across several live Gonka models + roles, one call.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a comprehensive answer.129 npm193MIT
- FlicenseNot gradedqualityBmaintenanceExposes multiple LLMs as individual tools via the OpenAI Responses API wire format, enabling the calling AI to get second opinions and orchestrate multi-model discussions with a quorum tool.137 npm1-
- AlicenseNot gradedqualityBmaintenanceFans out queries to multiple independent free LLMs from different providers and returns their answers side by side, enabling sanity-checking of decisions or getting multiple perspectives during coding sessions.GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables querying multiple AI models simultaneously and returns all answers unmerged for the user to weigh.4MIT