Nosana Agentic MCP

Nosana Agentic MCP

This MCP server enables AI agents to manage Nosana compute network deployments, jobs, scaling, and secrets through natural language.

Category
Visit Server

README

Nosana Agentic MCP

Welcome to the Nosana Agentic MCP repository! This project provides a powerful Model Context Protocol (MCP) server that integrates Nosana compute network deployments and jobs with AI agents.

By connecting this MCP server to your AI agent (such as Claude Desktop, Cursor, or any MCP-compatible client), you empower it to directly interact with the Nosana network. Your AI can now deploy AI models, monitor jobs, manage secrets, and control scaling—all through natural language.


🚀 Available AI Tools

The Nosana MCP Server exposes a robust set of tools allowing AI agents to fully manage your compute infrastructure:

  • Deployment Management: deploy_model, list_deployments, get_deployment, restart_deployment, stop_deployment
  • Scaling & Configuration: update_replicas, update_timeout, get_gpu_options
  • Job Execution: compose_job_definition, post_job_definition, list_jobs, get_job_status, stop_job, extend_job
  • Logs & Artifacts: get_deployment_logs, get_job_logs, download_artifacts, upload_secrets
  • Diagnostics: diagnose, analyze_model, get_ssh_command, check_market_queue

⚙️ Quick Start (IDE & Agent Integration)

You can seamlessly connect this MCP Server directly to your IDE or Agent. Simply provide the following configuration in your claude_desktop_config.json or your Cursor MCP settings.

{
  "mcpServers": {
    "nosana": {
      "command": "npx",
      "args": ["nosana-deployment-mcp"],
      "env": {
        "NOSANA_API_KEY": "your_nosana_api_key_here"
      }
    }
  }
}

Make sure to replace "your_nosana_api_key_here" with your actual API key.


🔒 Prerequisites & Security

  • Nosana Account: You need an active Nosana account.
  • API Key: Required to authenticate requests to the Nosana network.
  • Node.js: v18+ is required to run the npx command.

⚠️ Security Warning: Never commit your NOSANA_API_KEY to public repositories. Always use .env files or secure secret managers when developing locally.


🛠️ Local Development

If you want to contribute or run the MCP server from source:

  1. Clone the repository:
    git clone https://github.com/naveendhaterwal/Nosana-Agentic-Mcp.git
    cd Nosana-Agentic-Mcp/mcp-server
    
  2. Install dependencies:
    npm install
    
  3. Build the project:
    npm run build
    

🤝 Contributing

Contributions are welcome! Please open an issue or submit a Pull Request if you'd like to add new tools to the MCP server, fix bugs, or improve the documentation.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured