API Tools

safe4.ai

Provides pricing and payment authorization decisions for agent transactions.

x402 supported1 endpoint2 known toolsFirst detected August 28, 2026Last detected August 28, 2026

ENDPOINT 1

https://api.safe4.ai/mcp

No auth detected

MCP server metadata

Name: safe4
Version: 1.29.1

Capabilities

experimentalpromptsresourcestools

Server instructions

Safe4 decides whether an AI agent's proposed payment should be allowed, by testing the purchase against the task the agent was actually given. The distinguishing case is a payment that is inside every budget, in an allowed category, and to an approved counterparty, and is still denied because it does not serve the task. safe4_price is free. safe4_authorize is settled per call in USDC over x402: call it without a payment to receive the price list, then again with a payment payload.

Known tools 2

safe4_price

Price and accepted payment networks for one Safe4 decision.

Potential side effects

safe4_authorize

Decide whether a proposed agent payment should proceed.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.safe4]
url = "https://api.safe4.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "safe4": {
      "type": "http",
      "url": "https://api.safe4.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: safe4
Remote MCP URL: https://api.safe4.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "safe4": {
      "url": "https://api.safe4.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "safe4": {
      "type": "http",
      "url": "https://api.safe4.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "safe4",
  "transport": "streamable-http",
  "url": "https://api.safe4.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for safe4.ai was fetched 2026-08-29T17:31:10.299Z.

Trust status Neutral

safe4.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.