Neurolink
๐ โ๏ธ ๐ ๐ ๐ช ๐ง - Making enterprise AI infrastructure universally accessible. Edge-first platform unifying 12 providers and 100+ models with multi-agent orchestration, HITL workflows, guardrails middleware, and context summarization.
What is Neurolink?
Neurolink is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐ โ๏ธ ๐ ๐ ๐ช ๐ง - making enterprise ai infrastructure universally accessible. edge-first platform unifying 12 providers and 100+ models with multi-agent orchestration, hitl workflows, guardrails mid...
๐ โ๏ธ ๐ ๐ ๐ช ๐ง - Making enterprise AI infrastructure universally accessible. Edge-first platform unifying 12 providers and 100+ models with multi-agent orchestration, HITL workflows, guardrails middleware, and context summarization.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ๐ โ๏ธ ๐ ๐ ๐ช ๐ง - Making enterprise AI infrastructure universal
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @juspay/neurolinkManual Installation
npx -y @juspay/neurolinkConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Neurolink
Neurolink (@juspay/neurolink) is an enterprise AI infrastructure platform that unifies access to 33+ LLM providers โ including OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Ollama, DeepSeek, and more โ through a single consistent API. It ships as an MCP server that adds multi-agent orchestration, human-in-the-loop (HITL) approval workflows, guardrails middleware, context summarization, multimodal file processing, and built-in RAG to any MCP-compatible AI client. Teams use it to standardize their AI stack, add enterprise-grade safety controls, and switch between providers without changing application code.
Prerequisites
- Node.js 18+ installed
- API keys for at least one supported LLM provider (e.g. ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_AI_API_KEY)
- Optional: Redis instance for distributed conversation memory (REDIS_URL)
- An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
Install the Neurolink package
Install @juspay/neurolink from npm, or use npx to run it without a global install.
npm install @juspay/neurolink
# or run directly
npx @juspay/neurolink --helpSet your provider API key environment variables
Export API keys for the providers you want to use. At minimum, set one provider key. Neurolink will auto-select a provider based on available keys.
export ANTHROPIC_API_KEY="your-anthropic-key"
export OPENAI_API_KEY="your-openai-key"
export GOOGLE_AI_API_KEY="your-google-key"Add Neurolink to your MCP client configuration
Register the server in claude_desktop_config.json, passing provider keys as environment variables so the server can authenticate with upstream LLMs.
{
"mcpServers": {
"neurolink": {
"command": "npx",
"args": ["-y", "@juspay/neurolink"],
"env": {
"ANTHROPIC_API_KEY": "your-anthropic-key",
"OPENAI_API_KEY": "your-openai-key"
}
}
}
}Restart your MCP client
Restart Claude Desktop or your chosen MCP client to activate Neurolink. Tools for generation, streaming, RAG, file analysis, and provider management will become available.
Use Neurolink to route tasks to different providers
Ask your AI assistant to generate content, analyze documents, or run code tasks using a specific provider or model. Neurolink handles provider selection, fallback, and response normalization automatically.
Neurolink Examples
Client configuration
Example claude_desktop_config.json for Neurolink with multiple provider keys.
{
"mcpServers": {
"neurolink": {
"command": "npx",
"args": ["-y", "@juspay/neurolink"],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-...",
"OPENAI_API_KEY": "sk-...",
"GOOGLE_AI_API_KEY": "AIza..."
}
}
}
}Prompts to try
Example prompts demonstrating multi-provider routing, RAG, and HITL workflows.
- "Use GPT-4o to summarize this PDF: [attach file]"
- "Generate a haiku using Claude Sonnet and then the same prompt using Gemini, and compare the results"
- "Search my uploaded documents for anything about refund policies"
- "Analyze this CSV file and produce a statistical summary"
- "List all available LLM providers and their current status"Troubleshooting Neurolink
No provider available error on startup
Ensure at least one provider API key is set in the environment. Check that the key name matches exactly: ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_AI_API_KEY, etc. Run 'npx @juspay/neurolink --help' to verify the installation.
Redis connection errors for conversation memory
If you do not have Redis, either omit the REDIS_URL variable (memory will use an in-process SQLite fallback) or set REDIS_URL to a running Redis instance URL such as redis://localhost:6379.
HITL approval dialogs not appearing
HITL workflows require an MCP client that supports interactive tool confirmation. Ensure your client version supports this. For Claude Desktop, update to the latest version. HITL is configured programmatically via the hitl.requireApproval option.
Frequently Asked Questions about Neurolink
What is Neurolink?
Neurolink is a Model Context Protocol (MCP) server that ๐ โ๏ธ ๐ ๐ ๐ช ๐ง - making enterprise ai infrastructure universally accessible. edge-first platform unifying 12 providers and 100+ models with multi-agent orchestration, hitl workflows, guardrails middleware, and context summarization. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Neurolink?
Install via npm with the command: npx -y @juspay/neurolink. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Neurolink?
Neurolink works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Neurolink free to use?
Yes, Neurolink is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Neurolink Alternatives โ Similar Cloud Services Servers
Looking for alternatives to Neurolink? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
โ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
โ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
โ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
โ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
โ 26.7kๆฌ้กน็ฎไธบxiaozhi-esp32ๆไพๅ็ซฏๆๅก๏ผๅธฎๅฉๆจๅฟซ้ๆญๅปบESP32่ฎพๅคๆงๅถๆๅกๅจใBackend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
โ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Neurolink in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Neurolink?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.