HydraMCP

<p align="center">
  <img src="assets/HydraMCP.png" width="200" />
</p>

<h1 align="center">HydraMCP</h1>
<p align="center">Connect agents to agents.</p>

An MCP server that lets Claude Code query any LLM — compare, vote, and synthesize across GPT, Gemini, Gemini, and local models from one terminal.

## Quick Start

```bash
npx hydramcp setup
```

That's it. The wizard walks you through everything — API keys, subscriptions, local models. At the end it gives you the one-liner to add to Claude Code.

Or if you already have API keys:

```bash
Claude MCP add hydramcp -e OPENAI_API_KEY=sk-... -- npx hydramcp
```

## What It Looks Like

Four models, four ecosystems, one prompt. Real output from a live session:

```
> compare gpt-5-codex, gemini-3, gemini-sonnet, and local qwen on this function review

## Model Comparison (4 models, 11637ms total)

| Model                      | Latency         | Tokens |
|----------------------------|-----------------|--------|
| gpt-5-codex                | 1630ms fastest  | 194    |
| gemini-3-pro-preview       | 11636ms         | 1235   |
| gemini-sonnet-4-5-20250929 | 3010ms          | 202    |
| ollama/qwen2.5-coder:14b   | 8407ms          | 187    |
```

All four independently found the same async bug. Then each one caught something different the others missed.

And this is consensus with a local judge:

```
> get consensus from gpt-5, gemini-3, and gemini-sonnet. use local qwen as judge.

## Consensus: REACHED

Strategy: majority (needed 2/3)
Agreement: 3/3 models (100%)
Judge: ollama/qwen2.5-coder:14b (686ms)
```

Three cloud models polled, local model judging them. 686ms to evaluate agreement.

## Tools

| Tool | What It Does |
|------|-------------|
| **list_models** | See what's available across all providers |
| **ask_model** | Query any model, optional response distillation |
| **compare_models** | Same prompt to 2-5 models in parallel |
| **consensus** | Poll 3-7 models, LLM-as-judge evaluates agreement |
| **synthesize** |