Skip to content
anlyon.devby Anlyon

SCRIPTMASTERLABS — SML agent-safety

com.scriptmasterlabs/agent-safetyscriptmasterlabs.comstreamable-httpv1.0.0Scanned

Three fast safety checks for agents, each with a signed hash-chained receipt: (1) prompt-injection c

4 tools: 4 change things.

Tools: 0 delete, 0 irreversible, 4 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 2
  • No findings

Anlyon alternative

4 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →
Compare with similar serversMarkdownJSONReport this listing

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

4 tools

Changes things 4Claude Code: ask
  • catalogMachine-readable catalog with prices and 402 termsNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Machine-readable catalog with prices and 402 terms
  • prompt-injectionPrompt-injection check ($0.004 via x402 at POST https://sml-agent-safety.onrender.com/v1/prompt-injection).No 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.
    Description, as the server wrote it
    Prompt-injection check ($0.004 via x402 at POST https://sml-agent-safety.onrender.com/v1/prompt-injection). POST {text}. Verdict safe/suspicious/malicious + score + categories + matched spans + obfuscation tricks found + recommendation.

    Annotations the server declares

    • readOnlyHint: true
    • x402: [object Object]
  • url-safetyURL safety check ($0.004 via x402 at GET https://sml-agent-safety.onrender.com/v1/url-safety).Can 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

    • 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
    URL safety check ($0.004 via x402 at GET https://sml-agent-safety.onrender.com/v1/url-safety). GET ?url=. Verdict safe/suspicious/dangerous + score + reasons (lookalike, brand impersonation, domain age, redirects, seed-phrase/drainer content, agent-targeted injection).

    Annotations the server declares

    • readOnlyHint: true
    • x402: [object Object]
  • x402-healthx402 endpoint health / pay-readiness ($0.002 via x402 at GET https://sml-agent-safety.onrender.com/v1/x402-health).Can 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

    • 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
    x402 endpoint health / pay-readiness ($0.002 via x402 at GET https://sml-agent-safety.onrender.com/v1/x402-health). GET ?url=&method=GET|POST&maxUsd=. Live probe (never pays): go/caution/no_go, recommended payment option, every accepts problem, discovery + bazaar metadata, latency.

    Annotations the server declares

    • readOnlyHint: true
    • x402: [object Object]

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 or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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.

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-safety https://sml-agent-safety.onrender.com/mcp
claude mcp add --transport http agent-safety https://sml-agent-safety.onrender.com/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__agent-safety__prompt-injection",
      "mcp__agent-safety__url-safety",
      "mcp__agent-safety__x402-health",
      "mcp__agent-safety__catalog"
    ],
    "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 agent-safety. Review it before you use it.

Capability tags behind 2 rules
  • mcp__agent-safety__url-safety outbound
  • mcp__agent-safety__x402-health outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/com.scriptmasterlabs/agent-safety/verify?hash=66efd61022b446e92f87f118eb25d7d42c5a2d5123cdb577a9b73aaae84f7a13" | jq -e '.changed == false'

Pinned hash 66efd61022b4, from Nov 3, 2026, 20:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/com.scriptmasterlabs/agent-safety/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

anlyon.dev badge for com.scriptmasterlabs/agent-safety
[![anlyon.dev](https://anlyon.dev/badge/com.scriptmasterlabs/agent-safety.svg)](https://anlyon.dev/servers/com.scriptmasterlabs/agent-safety)

Source: MCP Registry. Synced Nov 3, 2026, 20:17 UTC.