MindBridge MCP Server The AI Router for Big Brain Moves

@pinkpixel-dev

代码仓库

基本信息

分类

AI 与智能体

许可证

MIT

传输方式

stdio

作者

pinkpixel-dev

关于 MindBridge MCP Server The AI Router for Big Brain Moves

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.

#chat #agent #mcp #agents #reasoning #second-brain #llm#reasoning-agent#llm-inference #model-context-protocol #mcp-server #modelcontextprotocol #model-context-protocol-servers

MindBridge MCP Server The AI Router for Big Brain Moves 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mindbridge-mcp": {
      "command": "npx",
      "args": [
        "@pinkpixel/mindbridge"
      ]
    }
  }
}

MindBridge MCP Server The AI Router for Big Brain Moves 工具

Get responses from various LLM providers

List all configured LLM providers and their available models

List all available models that support reasoning capabilities

概览

What is MindBridge MCP Server?

MindBridge MCP Server is a Model Context Protocol (MCP) server that unifies and orchestrates multiple LLM providers, enabling users to route tasks to different models and compare responses. It integrates with OpenAI, Anthropic, Google, DeepSeek, OpenRouter, Ollama, and any OpenAI-compatible API, serving agent builders and multi‑model workflow developers.

How to use MindBridge MCP Server?

Install globally via npm (npm install -g @pinkpixel/mindbridge), through Smithery, or by cloning the source repository. Configure environment variables with API keys for your chosen providers and optionally set provider‑specific defaults in the MCP configuration. Start the server with npx @pinkpixel/mindbridge or npm run dev, then invoke tools like getSecondOpinion, listProviders, and listReasoningModels by sending JSON requests.

Key features of MindBridge MCP Server

Multi-LLM support across OpenAI, Anthropic, Google, DeepSeek, OpenRouter, Ollama, and OpenAI‑compatible APIs.
Reasoning‑engine‑aware routing to models optimized for deep reasoning.
getSecondOpinion tool to compare responses from multiple models side by side.
OpenAI‑compatible API layer for drop‑in replacement in existing tools.
Auto‑detects providers from provided API keys.
Flexible configuration via environment variables, MCP config, or JSON.

Use cases of MindBridge MCP Server

Build multi‑model AI agents and orchestration engines.
Route reasoning‑heavy tasks to specialist models.
Compare model outputs side‑by‑side with getSecondOpinion.
Escape vendor lock‑in by easily switching between providers.
Integrate into existing tools that expect OpenAI endpoints.

常见问题

Which LLM providers are supported?

Supported providers include OpenAI, Anthropic, Google, DeepSeek, OpenRouter, Ollama (local models), and any OpenAI‑compatible API.

How do I configure API keys?

Set environment variables such as `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `DEEPSEE

AI 与智能体分类下的更多 MCP 服务器

APIXO AI

APIXO

Remote MCP for AI image, video, music, speech and custom voice generation. Discover models and input schemas for free; authorize your APIXO account to generate media and check results.

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

OpenZiti MCP Gateway

openziti

NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

botchelor

David Smith

Docs: https://botchelor.com/agents and https://botchelor.com/llms.txt . Botchelor is a blind-date show for fictional characters, and AI agents are welcome to play. Over MCP, your agent builds an original character in w

strac-mcp-dlp

strac-io

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi