Skip to main content
Glama

fusion-mcp

Local Fusion MCP server — replicates the OpenRouter Fusion mechanism on your local Claude CLI subscription. No OpenRouter, no separate token bill, one wallet.

Instead of dispatching to many vendors, it fans out several headless claude -p calls, each given a distinct analytical lens, then runs a judge pass and a synthesis pass.

Pipeline

Stage

Name

What

1

Panel

N parallel claude -p calls, diverse lenses (pragmatist / skeptic / researcher / architect), web search on

2

Judge

One call: consensus / contradictions / gaps / blind spots

3

Synthesis

One call: final answer grounded in the judge analysis

Related MCP server: Brutalist MCP

Tool

fusion_research(question, panel="default")

Panels:

  • default / frontier — Opus 4.8

  • budget — haiku + sonnet (use for frequent calls)

Install

Recommended — from PyPI via uvx (no manual venv, works in every folder):

claude mcp add -s user fusion -- uvx --from fusion-mcp fusion-mcp

-s user registers the server for all folders; uvx fetches fusion-mcp from PyPI on first run.

Plain pip works too:

pip install fusion-mcp
claude mcp add -s user fusion -- fusion-mcp

From source (clone, for hacking on it):

git clone https://github.com/Jolymmiles/fusion-mcp.git
cd fusion-mcp && python3 -m venv .venv && .venv/bin/pip install -e .
claude mcp add -s user fusion -- $(pwd)/.venv/bin/python $(pwd)/fusion_mcp.py

Requirements

Needs the Claude CLI (claude) on PATH and an active Claude Pro/Max subscription — the server fans out local claude -p calls. Without it the tool will not run.

Cost

Each call ≈ panel_size + 2 full Claude turns, 2-3x slower than a single call. Binding limit is the subscription request rate / usage quota, not dollars. Call sparingly — reserve for expensive questions: architecture decisions, comparing approaches, best-practice research.

Statusline (optional)

Server writes an atomic JSON heartbeat to $XDG_RUNTIME_DIR/fusion-mcp/state.json. Reader fusion-status.sh (bash + jq) prints e.g. 🔮 fusion[panel] 2/3 panel. Wire into statusLine.command in settings.json.

A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    -
    quality
    D
    maintenance
    Query multiple AI models (GPT-4, Claude, Gemini, Grok) in parallel for diverse perspectives. Get different expert viewpoints when stuck or need enhanced reasoning.
    Last updated
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Queries Claude Sonnet 4.6 and OpenAI GPT-5.5 in parallel via OpenRouter, returning structured multi-perspective responses for comparison and cross-checking.
    Last updated
    1
    4
    MIT

View all related MCP servers

Related MCP Connectors

  • Deliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus.

  • Persistent context for Claude. Your AI always knows your projects and next actions across sessions.

  • GA4 conversion analyst inside Claude — funnel drops, traffic anomalies, device gaps, with numbers.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Jolymmiles/fusion-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server