Back to search
100
MCP live MCP 2025-11-25 streamable-http

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

io.github.tjcgraham-rgb/gaip-broker

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

Website ↗
Watch this dependency Share evidence report
Uptime
100.0%
5 direct probes · 30d
Response
2565ms
last probe
Tools
5
callable
Resources
4
readable
Prompts
5
available
Primary URL
https://www.gaipagents.com/mcp
Score: 100/100
Handshake verified by our own probe.
pass Answers the MCP handshake 50/50
The handshake and the list calls succeeded on the primary URL.
pass Lists tools, resources or prompts 30/30
5 tools, 4 resources, 5 prompts returned.
pass 3 or more catalogue items 10/10
14 items in total; 3 or more earns these points.
pass Describes itself 10/10
96 characters; more than 30 earns these points.

Tools · 5

gaip_check

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. …

gaip_watch

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 (che…

gaip_diagnose

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_afte…

gaip_verify

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` w…

second_look_check

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…

Resources · 4

llms.txt

What GAIP is, the first call, the map of what it answers (by who asks), example calls and limits.

https://www.gaipagents.com/llms.txt
products

GAIP's products, the agents behind them and their tools (JSON).

https://www.gaipagents.com/v1/free/products
receipt-spec

How GAIP receipts, hash chain and Merkle proofs work, so any result can be checked later.

https://www.gaipagents.com/v1/free/evidence/receipt-spec
observatory-summary

Aggregate counts from the Agent Observatory: targets observed, status distribution and manifest changes in the last 7 days. No per-party ranking (JSON).

https://www.gaipagents.com/v1/free/observatory/summary

Prompts · 5

check_agent_before_use

Check whether an AI agent, A2A agent card, MCP server or OpenAPI service works and is reachable before you rely on it. Needs only its public https URL.

why_did_my_call_fail

Diagnose a failed call to an agent, MCP server or API from the error you got (HTTP status, JSON-RPC code or error text): cause, whether to retry and fix steps.

watch_mcp_server

Check an MCP server or agent now, then have GAIP re-check it every 24 hours and record each change with a receipt. Free: up to 3 watches.

did_supplier_deliver

Record what a good response from a public HTTPS service looks like, then have GAIP check what it actually returns. Neutral PASS / FAIL / UNKNOWN per check with a receipt.

verify_citations

Check that cited web pages are reachable and contain the quoted text. One citation per line as 'URL | quoted text'.

How to use

Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://www.gaipagents.com/mcp

Cursor or Cline: add to your MCP config:

{
  "mcpServers": {
    "gaip_\u2014_evidence_on_ai_agents_before_and_after_you_call_them": {
      "url": "https://www.gaipagents.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Source: github.com/tjcgraham-rgb/gaip-agents