Which integrations are available for this server?

Enables AI agents to interact with [OpenAI](/mcp/servers/integrations/openai)'s language models through their API, supporting conversation history, model switching, and extended reasoning capabilities for compatible models.

Polybrain MCP Server

An MCP (Model Context Protocol) server for connecting AI agents to multiple LLM models. Supports conversation history, model switching, and seamless Claude Code integration.

Features

Multi-model support (OpenAI, OpenRouter, custom endpoints)
Conversation history management
Switch models mid-conversation
Extended thinking/reasoning support (configurable by provider)
Pure MCP protocol (silent by default)
Automatic server management

Installation

npm install -g polybrain # or pnpm add -g polybrain

Quick Setup

1. Configure Models

Option A: YAML (recommended)

Create ~/.polybrain.yaml:

models: - id: "gpt-4o" modelName: "gpt-4o" baseUrl: "https://api.openai.com/v1" apiKey: "${OPENAI_API_KEY}" provider: "openai" - id: "gpt-5.1" modelName: "openai/gpt-5.1" baseUrl: "https://openrouter.io/api/v1" apiKey: "${OPENROUTER_KEY}" provider: "openrouter"

Set env vars:

export OPENAI_API_KEY="sk-..." export OPENROUTER_KEY="sk-or-..."

Option B: Environment variables

export POLYBRAIN_BASE_URL="https://api.openai.com/v1" export POLYBRAIN_API_KEY="sk-..." export POLYBRAIN_MODEL_NAME="gpt-4o"

2. Coding Agent Integration

Claude Code

Run the following command to add Polybrain to Claude Code:

claude mcp add -s user -t stdio polybrain -- polybrain

OpenAI Codex

Open ~/.codex/config.toml and add:

[mcpServers.polybrain] command = "polybrain"

Usage

You can now ask your coding agent to consult specific models. For example:

"Ask deepseek what's the best way to install python on mac"

Or:

"What models are available from polybrain?"

Configuration Reference

Environment Variables

POLYBRAIN_BASE_URL - LLM API base URL
POLYBRAIN_API_KEY - API key
POLYBRAIN_MODEL_NAME - Model name
POLYBRAIN_HTTP_PORT - Server port (default: 32701)
POLYBRAIN_LOG_LEVEL - Log level (default: info)
POLYBRAIN_DEBUG - Enable debug logging to stderr
POLYBRAIN_CONFIG_PATH - Custom config file path

YAML Config Fields

httpPort: 32701 # Optional truncateLimit: 500 # Optional logLevel: info # Optional models: # Required - id: "model-id" # Internal ID modelName: "actual-model-name" # API model name baseUrl: "https://api.url/v1" # API endpoint apiKey: "key or ${ENV_VAR}" # API key provider: "openai" # Optional: provider type for reasoning support

Supported Providers

The provider field enables provider-specific features like extended thinking/reasoning. If not specified, reasoning parameters will not be passed to the API (safe default).

Provider	Reasoning Support	Valid Values
OpenAI	YES	`"openai"`
OpenRouter	VARIES	`"openrouter"`

Examples:

Use provider: "openai" for OpenAI API models (GPT-4, o-series)
Use provider: "openrouter" for OpenRouter proxy service (supports 400+ models)
Omit provider field if your endpoint doesn't support reasoning parameters

Example with reasoning:

models: - id: "gpt-o1" modelName: "o1" baseUrl: "https://api.openai.com/v1" apiKey: "${OPENAI_API_KEY}" provider: "openai" # Enables reasoning support - id: "gpt-5.1" modelName: "openai/gpt-5.1" baseUrl: "https://openrouter.io/api/v1" apiKey: "${OPENROUTER_KEY}" provider: "openrouter" # Enables reasoning support

To use reasoning, set reasoning: true in the chat tool call. If the model and provider support it, you'll receive both the response and reasoning content.

Development

Setup

pnpm install

Build

pnpm build

Lint & Format

pnpm lint pnpm format

Type Check

pnpm type-check

Development Mode

pnpm dev

Project Structure

src/ ├── bin/polybrain.ts # CLI entry point ├── launcher.ts # Server launcher & management ├── http-server.ts # HTTP server ├── index.ts # Main server logic ├── mcp-tools.ts # MCP tool definitions ├── conversation-manager.ts ├── openai-client.ts ├── config.ts ├── logger.ts └── types.ts

Debugging

Enable debug logs to stderr:

{ "mcpServers": { "polybrain": { "command": "polybrain", "env": { "POLYBRAIN_DEBUG": "true" } } } }

Restart Server

After changing configuration in ~/.polybrain.yaml, restart the HTTP backend server:

polybrain --restart

This kills the background HTTP server. The next time you use polybrain, it will automatically start a fresh server with the updated configuration.

License

MIT

Polybrain MCP Server

Polybrain MCP Server

Features

Installation

Quick Setup

1. Configure Models

2. Coding Agent Integration

Claude Code

OpenAI Codex

Usage

Configuration Reference

Environment Variables

YAML Config Fields

Supported Providers

Development

Setup

Build

Lint & Format

Type Check

Development Mode

Project Structure

Debugging

Restart Server

License

Resources

Tools

New MCP Servers

Latest Blog Posts

MCP directory API