MCP.Market

Agentmetal MCP server

by agentmetal.dev·dev.agentmetal/agentmetal·v0.3.4·2 stars

Rent a Linux VPS from an AI agent: provision, SSH in, run commands. Pay USDC (x402) or card.

A91/100grade A
What users say
No reviews yet
Be the first
Safety scan
A91/100

not scanned yet

Adoption
Growing

2 stars52 downloads/wk

Reviews

Write one

Nobody has reviewed Agentmetal yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agentmetal tools

No tool declarations could be read from the package source. They show once the server is installed.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Agentmetal compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 88% of 4,460 AI and agents servers
GitHub stars
2
more than 65% of 2,711 AI and agents servers
Downloads a week
52
more than 43% of 1,538 AI and agents servers with a package

Release history: 3 versions in the registry since 2026-07-02, latest 2026-10-12, typically one every 97 days.

Install Agentmetal in Claude Code, Cursor or VS Code

Runs npx -y @agentmetal/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agentmetal -- npx -y @agentmetal/mcp
Add to Cursor

What the publisher says

From the Agentmetal repository's README, as published. We do not edit it. Read it on GitHub

@agentmetal/mcp

MCP server that exposes AgentMetal as tools, so an agent can discover → pay → provision → SSH in → run commands → manage → renew its own Linux server (VPS / cloud instance) with no human signup. Paid tools sign USDC payments over x402 v2 (or pay by card); the rest are plain HTTP.

Tools

13 tools. Paid tools sign a USDC/x402 payment; account-gated tools need AGENTMETALAPIKEY (amlive…) and ownership of the server.

Add-ons (currently API endpoints, not yet separate MCP tools): extra storage ($0.01/GB/day, attached block volume) via POST /v1/servers/{id}/storage and extra bandwidth ($2/TB beyond the 20 TB included) via POST /v1/servers/{id}/bandwidth.

Configuration (env)

Use with Claude Code

// .mcp.json (or claude mcp add)
{
  "mcpServers": {
    "agentmetal": {
      "command": "node",
      "args": ["packages/mcp/src/index.ts"],
      "env": {
        "WALLET_PRIVATE_KEY": "0x…",
        "AGENTMETAL_MAX_USDC": "50"
      }
    }
  }
}

The wallet must hold USDC on Base. The spend cap (AGENTMETALMAXUSDC) bounds what any single tool call can pay; a 402 above the cap is refused before signing.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agentmetal: common questions

Is Agentmetal MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Agentmetal safety report
How do I install Agentmetal?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agentmetal need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agentmetal maintained?
The last commit was 45 days ago (2026-09-20). The latest release is v0.3.4.
What can I use instead of Agentmetal?
Servers from other publishers that do the same job: Agoragentic Agent OS MCP server, Commands MCP server and Ausca MCP server.
How does Agentmetal compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); github stars 2 (more than 65% of 2,711 AI and agents servers); downloads a week 52 (more than 43% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to Agentmetal

Same job from other publishers: the closest match first, then the best rated.

  • Agoragentic Agent OS MCP
    Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.
    B
  • Commands
    Model Context Protocol server to run commands (tool: `runProcess`)
    A
  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A
  • Shellward
    AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
    A