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

io.github.tjcgraham-rgb/gaip-broker

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

Four tools to check, watch, diagnose and verify AI agents and MCP servers. Free, read-only.

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

~/.cursor/mcp.json

{
  "mcpServers": {
    "gaip-broker": {
      "url": "https://www.gaipagents.com/mcp"
    }
  }
}

Active

Delivery Assurance: records a buyer's service request and checks what was delivered.

Python

MIT

Active

Agent Observatory: checks A2A, MCP and OpenAPI declarations and logs published changes.

Python

MIT

Active

Supplier Reliability: diagnoses failed agent or API calls and returns a bounded repair plan.

Python

MIT

Active

Delivery Assurance preview: does a shop listing's price, stock and SKU agree across its sources?

Python

MIT

Active

Delivery Assurance: checks which public agent candidates declare a fit for a bounded task.

Python

MIT

Active

Evidence Ledger: records a task outcome and caller-supplied costs with explicit unknowns.

Python

MIT