Skip to content

GAIP — evidence on AI agents before and after you call them MCP server

io.github.tjcgraham-rgb/gaip-brokertjcgraham-rgbstreamable-httpv1.8.0Scanned

GAIP keeps an independent, dated record of what AI agents, MCP servers and online shops publish.

5 tools: 5 change things.

Tools: 0 delete, 0 irreversible, 5 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 5
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the GAIP — evidence on AI agents before and after you call them MCP server can do

The GAIP — evidence on AI agents before and after you call them MCP server is published by the GitHub account tjcgraham-rgb. It has 5 tools. It can create or change data (5 tools: gaip_check, gaip_watch, gaip_diagnose, gaip_verify and 1 more), but cannot delete data. None of its tools only reads.

4 tools bring in text other people can write (gaip_check, gaip_watch, gaip_verify and 1 more); 5 tools can send data out of your system (gaip_check, gaip_watch, gaip_diagnose and 2 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.8.0.

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.

5 tools

Changes things 5Claude Code: ask
  • gaip_checkUse this when asked whether an AI agent, MCP server or API works or has changed, e.g.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
    Use this when asked whether an AI agent, MCP server or API works or has changed, e.g. before adding or paying it. Pass its `url`. Returns a verdict, fixes, dated history when observed, and a receipt. With `agent` (e.g. GPTBot): may your bot fetch it (robots.txt, AI-crawler rules)? Free, read-only, no account; inputs must be public and non-personal.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • gaip_diagnoseUse this when an agent, MCP or API call failed.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
    Use this when an agent, MCP or API call failed. Paste the `error` text and/or `http_status`; add the service `url` if known. Returns the cause, the exact fix (e.g. the missing argument) and retry_after_seconds; `keep_receipt: true` adds a dated receipt. Free, read-only, no account; inputs must be public and non-personal.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • gaip_verifyUse this when asked whether a service delivered what was promised or whether cited pages contain the quoted text.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.

    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
    Use this when asked whether a service delivered what was promised or whether cited pages contain the quoted text. Pass `citations`, or a service `url` (+ `checks`, the `result` you got), or `claims` with `observations`. Returns a result per item. Free, no account; only delivery keeps a record. Inputs must be public and non-personal.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • gaip_watchUse this when asked to keep an eye on an agent or MCP server, or to be alerted when it changes.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.

    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
    Use this when asked to keep an eye on an agent or MCP server, or to be alerted when it changes. Pass its `url`: returns feed links and its latest dated changes; add `webhook_url` for a free watch (checked every 24 h, signed webhook on change). Free, no account; with a webhook it records a watch. Inputs must be public and non-personal.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • second_look_checkUse this when a shopper is about to buy something an AI suggested, or asks if a price or stock claim is right.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
    Use this when a shopper is about to buy something an AI suggested, or asks if a price or stock claim is right. Pass the product page `url` and the `claim`. Returns what the page showed beside what the claim said, and a signed, dated receipt. Second Look by GAIP. Free, no account, no affiliate links; inputs must be public and non-personal.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: 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 write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out5
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.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:12 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.gaipagents.com/mcp: tools/list returned 5 tools to an anonymous client, including gaip_check (write), gaip_watch (write), gaip_diagnose (write), gaip_verify (write), second_look_check (write)

    What this check looks for

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.

Install

Pinned to version 1.8.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http gaip-broker https://www.gaipagents.com/mcp
claude mcp add --transport http gaip-broker https://www.gaipagents.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__gaip-broker__gaip_check",
      "mcp__gaip-broker__gaip_watch",
      "mcp__gaip-broker__gaip_diagnose",
      "mcp__gaip-broker__gaip_verify",
      "mcp__gaip-broker__second_look_check"
    ],
    "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 gaip-broker. Review it before you use it.

Capability tags behind 5 rules
  • mcp__gaip-broker__gaip_check untrusted-input, outbound
  • mcp__gaip-broker__gaip_watch untrusted-input, outbound
  • mcp__gaip-broker__gaip_diagnose outbound
  • mcp__gaip-broker__gaip_verify untrusted-input, outbound
  • mcp__gaip-broker__second_look_check untrusted-input, 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://radar.anlyon.com/api/v1/servers/io.github.tjcgraham-rgb/gaip-broker/verify?hash=da881f65606c9f202d18100cbcb7e15797b03f364440eea2adf449f068cb7a07" | jq -e '.changed == false'

Pinned hash da881f65606c, from Nov 20, 2026, 15:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.tjcgraham-rgb/gaip-broker/changes.xml

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

Badge

Anlyon Radar badge for io.github.tjcgraham-rgb/gaip-broker
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.tjcgraham-rgb/gaip-broker.svg)](https://radar.anlyon.com/servers/io.github.tjcgraham-rgb/gaip-broker)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.

GAIP — evidence on AI agents before and after you call them MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the GAIP — evidence on AI agents before and after you call them MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the GAIP — evidence on AI agents before and after you call them MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the GAIP — evidence on AI agents before and after you call them MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the GAIP — evidence on AI agents before and after you call them MCP server have?

5 tools: 5 write. gaip_check, gaip_watch, gaip_diagnose, gaip_verify and second_look_check.

Does the GAIP — evidence on AI agents before and after you call them MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the GAIP — evidence on AI agents before and after you call them MCP server send data to outside services?

5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): gaip_check, gaip_watch, gaip_diagnose, gaip_verify and second_look_check.

Has the GAIP — evidence on AI agents before and after you call them MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.