What is multimodels-mcp CLAUDE.md?

A local MCP server that lets Claude Code hand tasks to other AI models and receive their results for review. It can connect to Codex, DeepSeek, z.ai, OpenRouter, and models running through LM Studio.

Use it to delegate coding, research, or writing tasks from Claude Code to another model, including a model running on your own computer. It is configured and run locally on a Mac.

It avoids switching between separate AI tools when you want different models to handle parts of a task. A local control panel also lets you manage API keys and choose which models are enabled.

How dpmadsen/multimodels-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dpmadsen/multimodels-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dpmadsen/multimodels-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dpmadsen/multimodels-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dpmadsen/multimodels-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dpmadsen/multimodels-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dpmadsen/multimodels-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dpmadsen/multimodels-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dpmadsen/multimodels-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dpmadsen/multimodels-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,334 This file is loaded in full into every session.

When invoked 1,334 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 92% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01334	$0.01334
Opus 5.5	$0.00534	$0.00534
Sonnet 5.5	$0.00267	$0.00267
Haiku 4.5	$0.00133	$0.00133

Measured 2mo ago against content hash 4a7bde342d63, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

multimodels-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

92% identical to multimodels-mcp AGENTS.md — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Projeto: multimodels-mcp

English version: CLAUDE.en.md

O que é

Servidor MCP que funciona como um "garçom" entre o Claude Code e outros modelos de IA: o Claude delega uma tarefa, o servidor processa com o modelo escolhido e devolve o resultado pro Claude avaliar. Modelos disponíveis: Codex (via assinatura do ChatGPT, pelo CLI codex já instalado no Mac), DeepSeek, z.ai e OpenRouter (via chaves de API) e modelos locais via LM Studio. Inclui um painel de controle local pra gerenciar chaves e habilitar/desabilitar modelos.

Pra quem é

Pro Daniel, uso pessoal, rodando só no Mac dele dentro do Claude Code.

Stack e comandos

Servidor: TypeScript + SDK oficial de MCP da Anthropic (transporte stdio, roda local)
Conector universal: padrão OpenAI-compatible (atende DeepSeek, z.ai, OpenRouter e LM Studio — provedor novo = 1 linha de configuração + chave no .env)
Codex: integração via CLI codex (usa a assinatura, sem custo de API)
Painel de configuração: shadcn/ui + Tailwind (Vite, pasta ui/), página local no navegador — abrir com npm run panel (http://127.0.0.1:4747); depois de mudar código da interface, npm run build:ui
Configuração de modelos: arquivo local config/models.json (sem banco de dados)
Chaves: SEMPRE no .env (nunca no models.json, nunca no código)
Rodar os testes: npm test (compila e testa; os testes vivem em src/*.test.ts)
Compilar depois de mudar código: npm run build (o Claude Code executa o resultado em dist/)
O servidor está registrado no Claude Code com o nome multimodels (escopo user, vale pra todos os projetos); conferir com claude mcp list
Ferramentas expostas: list_models (cardápio) e delegate_task (delegação)

Como trabalhar comigo

Sobre mim

Eu NÃO sei programar. Já fiz projetos de vibecoding, mas preciso de direcionamento.
Explique tudo em português, com analogias do dia a dia. NUNCA assuma que sei termos técnicos.
Respostas objetivas. Se eu quiser mais detalhes, eu peço.

Read the full file on GitHub · 62 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 62 lines · 1,334 tokens per session scan A 4a7bde342d63

Subscribe to this mod's changes

multimodels-mcp CLAUDE.md is an instructions file published in the GitHub repository dpmadsen/multimodels-mcp (21 stars, last pushed 3mo ago), licensed MIT. It adds 1,334 tokens to every session, about $0.0053 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to multimodels-mcp AGENTS.md, differing in 11 lines, and is treated as a copy.

Building agents

multimodels-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
multimodels-mcp CLAUDE.mddpmadsen/multimodels-mcp	Instructions file	21	3mo ago	MIT	A	1,334	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

multimodels-mcp: Instructions file for Claude Code