MindBridge

v1.0.0Coding Agentsstable

MindBridge is an AI orchestration MCP server that lets any app talk to any LLM — OpenAI, Anthropic, DeepSeek, Ollama, and more — through a single unified API. Route queries, compare models, get second opinions, and build smarter multi-LLM workflows.

agentagentschatllmllm-inference
Share:
34
Stars
0
Downloads
0
Weekly
0/5

What is MindBridge?

MindBridge is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mindbridge is an ai orchestration mcp server that lets any app talk to any llm — openai, anthropic, deepseek, ollama, and more — through a single unified api. route queries, compare models, get second...

MindBridge is an AI orchestration MCP server that lets any app talk to any LLM — OpenAI, Anthropic, DeepSeek, Ollama, and more — through a single unified API. Route queries, compare models, get second opinions, and build smarter multi-LLM workflows.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MindBridge is an AI orchestration MCP server that lets any a

Use Cases

Route queries to multiple LLMs
Compare AI models
Build multi-LLM workflows
pinkpixel-dev

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedMay 2, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mindbridge-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MindBridge

MindBridge is an AI orchestration MCP server that unifies access to multiple large language model providers — OpenAI, Anthropic, Google Gemini, DeepSeek, OpenRouter, Ollama (local), and any OpenAI-compatible endpoint — through a single set of MCP tools. It exposes a getSecondOpinion tool for querying any configured model, a listProviders tool for discovering available providers and models, and a listReasoningModels tool for identifying models optimised for deep reasoning tasks. Developers and AI agent builders use it to route queries to the most capable or cost-effective model, compare responses across providers, and build multi-LLM workflows without managing multiple APIs individually.

Prerequisites

  • Node.js (LTS version recommended)
  • At least one LLM provider API key: OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY, DEEPSEEK_API_KEY, or OPENROUTER_API_KEY
  • Optional: Ollama running locally at http://localhost:11434 for local model support
  • An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
  • npm or npx available
1

Install MindBridge from npm

Install the package globally so it can be referenced by name in your MCP config, or use npx to run it on demand without installation.

npm install -g @pinkpixel/mindbridge
2

Obtain API keys for the providers you want to use

MindBridge auto-detects configured providers based on which API keys are present. You only need keys for the providers you intend to use. At least one key is required.

# Set one or more of these in your shell or .env file
export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...
export GOOGLE_API_KEY=AIza...
export DEEPSEEK_API_KEY=sk-...
export OPENROUTER_API_KEY=sk-or-...
3

Add MindBridge to your MCP client configuration

Edit your client's MCP config file. The example below uses npx to run the latest version and passes all supported API keys via the env block.

{
  "mcpServers": {
    "mindbridge": {
      "command": "npx",
      "args": ["-y", "@pinkpixel/mindbridge"],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY",
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_KEY",
        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY",
        "DEEPSEEK_API_KEY": "YOUR_DEEPSEEK_KEY",
        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY"
      }
    }
  }
}
4

Optional: configure Ollama for local models

If you run Ollama locally, set OLLAMA_BASE_URL. MindBridge will query the Ollama API to discover available models automatically.

export OLLAMA_BASE_URL=http://localhost:11434
5

Restart your MCP client and verify available providers

After restarting, ask the assistant to call the listProviders tool to confirm which providers and models MindBridge has detected from your API keys.

MindBridge Examples

Client configuration

Claude Desktop configuration for MindBridge with multiple provider keys and optional per-provider defaults.

{
  "mcpServers": {
    "mindbridge": {
      "command": "npx",
      "args": ["-y", "@pinkpixel/mindbridge"],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY",
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_KEY",
        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY",
        "DEEPSEEK_API_KEY": "YOUR_DEEPSEEK_KEY",
        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY",
        "OLLAMA_BASE_URL": "http://localhost:11434"
      }
    }
  }
}

Prompts to try

Prompts that exercise MindBridge's multi-LLM routing and comparison capabilities.

- "Ask GPT-4o what the key considerations are for database sharding"
- "Get a second opinion from DeepSeek reasoner on this architecture decision: [paste your design]"
- "List all the LLM providers and models currently available through MindBridge"
- "Ask Claude and GPT-4o the same question and compare their answers: what are the tradeoffs between microservices and monoliths?"
- "Use a reasoning model to evaluate this code for potential security vulnerabilities: [paste code]"
- "List which models are optimised for deep reasoning tasks"

Troubleshooting MindBridge

listProviders returns an empty list or fewer providers than expected

MindBridge only activates providers whose API key environment variables are set. Check that the keys are present in the env block of your MCP config (not just in your shell, since the MCP server inherits only the env block values in Claude Desktop).

getSecondOpinion returns an authentication error for a provider

Verify the API key for that provider is correct and has not expired. For OpenRouter, ensure your account has credits. For Ollama, confirm the service is running at OLLAMA_BASE_URL.

npx install is slow or fails on first run

The first run downloads the npm package. If you are behind a corporate proxy, configure npm proxy settings with `npm config set proxy http://proxy:port`. To avoid repeated downloads, install globally with `npm install -g @pinkpixel/mindbridge` and change the command in the config to `mindbridge`.

Frequently Asked Questions about MindBridge

What is MindBridge?

MindBridge is a Model Context Protocol (MCP) server that mindbridge is an ai orchestration mcp server that lets any app talk to any llm — openai, anthropic, deepseek, ollama, and more — through a single unified api. route queries, compare models, get second opinions, and build smarter multi-llm workflows. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MindBridge?

Follow the installation instructions on the MindBridge GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MindBridge?

MindBridge works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MindBridge free to use?

Yes, MindBridge is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mindbridge-mcp-server": { "command": "npx", "args": ["-y", "mindbridge-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MindBridge?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides