Safe4 is an MCP server with 2 tools an agent can call, among them safe4_authorize, safe4_price. It answers at https://api.safe4.ai/mcp/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
safe4_authorize | Decide whether a proposed agent payment should proceed. Settled per call in USDC over x402. Called without ``payment`` it returns the price list rather than a decision; call it again with the signed payload to receive one. The task and the Inputs: task, purchase, purchase_purpose, amount, currency, counterparty |
safe4_price | Price and accepted payment networks for one Safe4 decision. Free to call. Returns the same x402 terms the HTTP endpoint advertises, so an agent can see the cost before committing to a paid call. |
Every block below points at https://api.safe4.ai/mcp/. Pick your client and copy.
claude mcp add --transport http safe4 https://api.safe4.ai/mcp/
{
"mcpServers": {
"safe4": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.safe4.ai/mcp/"]
}
}
}{
"mcpServers": {
"safe4": {
"url": "https://api.safe4.ai/mcp/"
}
}
}{
"servers": {
"safe4": {
"type": "http",
"url": "https://api.safe4.ai/mcp/"
}
}
}{
"context_servers": {
"safe4": {
"url": "https://api.safe4.ai/mcp/"
}
}
}{
"mcpServers": {
"safe4": {
"serverUrl": "https://api.safe4.ai/mcp/"
}
}
}{
"mcpServers": {
"safe4": {
"url": "https://api.safe4.ai/mcp/"
}
}
}name: Safe4
version: 0.0.1
schema: v1
mcpServers:
- name: Safe4
type: streamable-http
url: https://api.safe4.ai/mcp/{
"mcpServers": {
"safe4": {
"httpUrl": "https://api.safe4.ai/mcp/"
}
}
}{
"mcpServers": {
"safe4": {
"type": "http",
"url": "https://api.safe4.ai/mcp/"
}
}
}{
"mcpServers": {
"safe4": {
"url": "https://api.safe4.ai/mcp/"
}
}
}goose://extension?url=https%3A%2F%2Fapi.safe4.ai%2Fmcp%2F&type=streamable_http&id=safe4&name=Safe4
It answered our last check on 17 October 2026 in 362 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by safe4.ai and served from api.safe4.ai, the vendor's own domain: https://api.safe4.ai/mcp/.
2, as returned by the server's own tools/list on 8 September 2026: safe4_authorize, safe4_price.
It answered our last check on 17 October 2026 in 362 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.safe4.ai/mcp/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.safe4. Endpoint host: api.safe4.ai. ARD identifier: urn:air:ai.safe4:mcp:safe4.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.