Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Paperspace with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Provision and track powerful GPU workloads via Paperspace. list compute instances, fetch active deployments, trace team projects, and query Gradient environmen

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 6 capabilities

The complete Paperspace capability set.

These are the exact actions your AI can choose when you ask it to work with Paperspace.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Paperspace.

  1. 01

    List notebooks

    Inspect deep internal arrays mitigating specific AI workload limits

  2. 02

    Get machine details

    Perform structural extraction of properties driving active Instance logic

  3. 03

    Get user details

    Identify precise active arrays spanning native Identity Auth

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Paperspace.

  1. 04

    List deployments

    Retrieve explicit Cloud logging tracing explicit Deploy targets

  2. 05

    List machines

    Identify bounded Compute resources inside the Headless Paperspace limits

  3. 06

    List projects

    Enumerate explicitly attached structured rules exporting active Team limits

Observed, not estimated

820ms average. Fast in production.

Paperspace is checked daily against the live service.

Daily averagePeak 1273ms
Aug 20Today
Fastest day
658ms
Slowest day
1273ms
14-day trend
Slowing+18%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Paperspace, so you can see the experience inside your AI.

It does not authenticate your account with Paperspace. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Paperspace Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_w4nfco02fghsGPeqz307rO7rx1srVWdx33BhZToR/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Paperspace capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "paperspace-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_w4nfco02fghsGPeqz307rO7rx1srVWdx33BhZToR/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Paperspace owners ask.

  • 01

    Are Paperspace Core machines dynamically mapped?

    Yes. The list_machines query returns deeply structured attributes associated exactly with the base compute objects provisioning storage arrays, IPs, and states running natively over Paperspace Core.

  • 02

    Can I spin up new Jupyter Gradient instances?

    Currently, this module focuses strictly on dynamic observability. pulling down Notebooks arrays, Teams constraints, and extracting native deploy mapping contexts. Write operations to spin up environments are out-of-scope for read workflows.

  • 03

    How do I fetch the resource specs belonging to a specific ID?

    After listing the overall arrays, provide the psxxxxxx ID identifier securely to the get_machine_details extractor to generate raw hardware limitations mapped logically inside that node.

Explore

More in Superpower

Suggestions