Angel Agent Guard: pre-purchase check + prompt-injection scan

● Active

com.oroboros-design.angel/agent-guard

Check a shop, checkout or payment link, paid API or token before paying; prompt-injection scan.

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "agent-guard": {
      "command": "npx",
      "args": [
        "-y",
        "angel-agent-guard@0.2.0"
      ],
      "env": {
        "ANGEL_AGENT_PRIVATE_KEY": "<your ANGEL_AGENT_PRIVATE_KEY>"
      }
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --env ANGEL_AGENT_PRIVATE_KEY='<your ANGEL_AGENT_PRIVATE_KEY>' --transport stdio agent-guard -- npx -y angel-agent-guard@0.2.0
OpenAI Codex CLI
codex mcp add agent-guard --env ANGEL_AGENT_PRIVATE_KEY='<your ANGEL_AGENT_PRIVATE_KEY>' -- npx -y angel-agent-guard@0.2.0
VS Code
code --add-mcp '{"name":"agent-guard","type":"stdio","command":"npx","args":["-y","angel-agent-guard@0.2.0"],"env":{"ANGEL_AGENT_PRIVATE_KEY":"<your ANGEL_AGENT_PRIVATE_KEY>"}}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

Environment variables
  • ANGEL_AGENT_PRIVATE_KEYsecretOptional hot-wallet key for automatic x402 payment (needs viem)

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Finance
Version
0.2.0
Registry
active
Published
11/14/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: Angel Agent Guard: pre-purchase check + prompt-injection scan is maintained, open source.

Maintained
Active
Last commit 6 days ago (Nov 16, 2026), 0 open issues.
Official registry
Active
Published as com.oroboros-design.angel/agent-guard in the official MCP registry, version 0.2.0.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
On your machine
A local npm package started by your client; it can reach whatever your user account can.
Credentials
1 required
Declared environment variables: ANGEL_AGENT_PRIVATE_KEY. They stay on your machine; the config on this page shows where each goes.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself.

On GitHub

read Nov 22, 2026
Stars
0
Forks
0
Last push
Nov 16, 2026
License
MIT

TypeScriptai-agentsbasecoinbase-agentkitmcpmcp-serverprompt-injectionusdcx402

From the README

angel-agent-guard New in 0.4: Angel Shield, the spend firewall for agents with a wallet Before your agent pays, shieldCheck answers allow, hold or block, with reasons. One call checks your spend rules (per-payment cap, daily budget reserved atomically so parallel agents cannot overspend, allow/block lists, chains, tokens, approval threshold, hold new merchants, kill switch), the merchant URL, the text that triggered the payment (prompt injection) and non-USDC tokens. Wallet limits check how much; Shield also checks why. Fail-closed: if Shield cannot be reached, the decision is hold and nothing is signed. See the replay of the May 2026 Grok × Bankrbot wallet drain: https://angel.oroboros-design.com/shield/lab Plus the guards an AI agent should run before it acts: • guardUntrusted(textOrUrl): before the model reads a web page, email, document, RAG chunk or tool result written by someone else. It runs a local pass first (invisible Unicode, tag smuggling, exfiltration images), then a hosted scan in 17 languages for text aimed at the model. • verifyBeforePay(urlOrToken): before any online purchase or paid call. That covers a shop or product page, a checkout or payment link (Stripe, Shopify, PayPal, SaaS checkout), an unknown API, an x402 endpoint, and a token swap or approval.…

Read the full README on GitHub →

Alternatives to Angel Agent Guard: pre-purchase check + prompt-injection scan

All Angel Agent Guard: pre-purchase check + prompt-injection scan alternatives →Best Finance servers →

The most-starred Finance servers in the index, with their live-check result.

ServerStarsLast pushLive check
CCXT44,949Nov 2026Local / not checked
QR Rápido7,477Nov 2026Needs sign-in
Finance Toolkit5,554Nov 2026Needs sign-in
AKQuant2,627Nov 2026Local / not checked
com.stripe MCP2,072Nov 2026Needs sign-in

Angel Agent Guard: pre-purchase check + prompt-injection scan: questions people ask

Is Angel Agent Guard: pre-purchase check + prompt-injection scan a remote or a local MCP server?
According to its entry in the official MCP registry, Angel Agent Guard: pre-purchase check + prompt-injection scan ships as a local package (npm) that your client starts on your machine.
Does Angel Agent Guard: pre-purchase check + prompt-injection scan need an API key?
Its registry entry declares one required environment variable: ANGEL_AGENT_PRIVATE_KEY. The config on this page shows where each goes.
Is Angel Agent Guard: pre-purchase check + prompt-injection scan safe to use?
Looks healthy: Angel Agent Guard: pre-purchase check + prompt-injection scan is maintained, open source. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: On your machine; credentials: 1 required. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is Angel Agent Guard: pre-purchase check + prompt-injection scan still maintained?
Active: the repository's last commit 6 days ago. Last push Nov 16, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 22, 2026.
How do I add Angel Agent Guard: pre-purchase check + prompt-injection scan to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.

More from daoudandiaye98-alt

All 6 servers by daoudandiaye98-alt →
  1. Mare Liberum · the open sea for agentsFirst stop for agents: read any page as Markdown, check sites, shared memory, buy for people.
  2. Mare Liberum · the open sea for agentsThe open sea for agents: call a need, get stores, products, prices and the routes that worked.
  3. Base Token Audit — ERC-20 honeypot check and swap route dataERC-20 honeypot and rug-pull check on Base and Ethereum, plus free swap route data.
  4. Checkout Guard — pre-purchase check for shops, payment links and paid APIsPre-purchase check for any shop, checkout or payment link, paid API or x402 endpoint.
Browse all Finance →

Add the badge to your site

Show visitors that Angel Agent Guard: pre-purchase check + prompt-injection scan is listed here — it’s also the link we check for a free listing.

Angel Agent Guard: pre-purchase check + prompt-injection scan — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/com-oroboros-design-angel-agent-guard?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Angel Agent Guard: pre-purchase check + prompt-injection scan — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Angel Agent Guard: pre-purchase check + prompt-injection scan — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/com-oroboros-design-angel-agent-guard?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/com-oroboros-design-angel-agent-guard) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/com-oroboros-design-angel-agent-guard) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/com-oroboros-design-angel-agent-guard)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/com-oroboros-design-angel-agent-guard"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/com-oroboros-design-angel-agent-guard"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/com-oroboros-design-angel-agent-guard"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).