Spheron Network

Provides compute deployment, wallet balance checks, deployment URLs, and lease details via MCP endpoints.

typescript

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "spheronfdn-spheron-mcp-plugin": {
      "command": "node",
      "args": [
        "/absolute/path/to/spheron-mcp-plugin/mcp-server/build/index.js"
      ],
      "env": {
        "YAML_API_URL": "http://149.56.15.95:8080/generate",
        "SPHERON_NETWORK": "testnet",
        "PROVIDER_PROXY_URL": "https://provider-proxy.sphn.xyz",
        "SPHERON_PRIVATE_KEY": "your-spheron-private-key"
      }
    }
  }
}

You can deploy, manage, and monitor compute deployments directly through the MCP interface powered by the Spheron Protocol SDK. This MCP server enables you to deploy YAML-defined compute resources, check wallet balances, fetch deployment URLs, and retrieve lease details with streamlined, in-editor configuration and run-time commands.

How to use

Use the MCP client to deploy compute resources, inspect deployment URLs, check your wallet balance for different tokens, and retrieve lease details. You interact with the MCP server through commands and configurations that run locally or remotely, depending on your setup. Start by ensuring your MCP server is running via your preferred method, then issue high-level requests through Claude or your MCP client to perform the following actions.

Deploy Compute

version: "1.0"

services:
  py-cuda:
    image: quay.io/jupyter/pytorch-notebook:cuda12-pytorch-2.4.1
    expose:
      - port: 8888
        as: 8888
        to:
          - global: true
    env:
      - JUPYTER_TOKEN=sentient
profiles:
  name: py-cuda
  duration: 2h
  mode: provider
  tier:
    - community
  compute:
    py-cuda:
      resources:
        cpu:
          units: 8
        memory:
          size: 16Gi
        storage:
          - size: 200Gi
        gpu:
          units: 1
          attributes:
            vendor:
              nvidia:
                - model: rtx4090
  placement:
    westcoast:
      attributes:
        region: us-central
      pricing:
        py-cuda:
          token: CST
          amount: 10

deployment:
  py-cuda:
    westcoast:
      profile: py-cuda
      count: 1

Or say:

Deploy this jupyter notebook on Spheron

Check Wallet Balance

What's my CST balance on Spheron?

Get Deployment URLs

Show me the URLs for my deployment with lease ID 12345

Get Lease Details

Get details for lease ID 12345

Available tools

Deploy Compute

Deploys a YAML-defined compute resource with specified resources, placement, and deployment count.

Check Wallet Balance

Queries the wallet balance for tokens associated with your MCP account.

Get Deployment URLs

Retrieves the URLs for active deployments and leases.

Get Lease Details

Fetches detailed information about a lease using its lease ID.

Built by

VeilStrat

AI signals for GTM teams