Skip to content

Sentinel

by 448c.org · remote · no sign-in to list tools · v0.0.1 · published by org.448c

Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.

Changes · 2
CompareRegistry entry

2 tools: 2 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http sentinel https://448c.org/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 2Claude Code: ask
  • check_addressCheck whether a crypto address is safe to transact with.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Check whether a crypto address is safe to transact with. Screens OFAC sanctions + community scam lists and flags contract-vs-wallet. Returns verdict (safe/caution/avoid), 0-100 risk score, reasons, and sources.

    Annotations the server declares

    • title: Check address safety
    • readOnlyHint: true
    • openWorldHint: true
    • paymentHint: true
  • check_urlCheck whether a URL or domain is a scam/phishing site.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Check whether a URL or domain is a scam/phishing site. Screens the MetaMask crypto-phishing blocklist, domain age (RDAP), and lexical red flags. Returns verdict (safe/caution/avoid), 0-100 risk score, reasons, and sources.

    Annotations the server declares

    • title: Check URL safety
    • readOnlyHint: true
    • openWorldHint: true
    • paymentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 0.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http sentinel https://448c.org/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__sentinel__check_address",
      "mcp__sentinel__check_url"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as sentinel. Review it before you use it.

Capability tags behind 2 rules
  • mcp__sentinel__check_address untrusted-input
  • mcp__sentinel__check_url untrusted-input, outbound