Home / MCP registry index / io.github.tjcgraham-rgb/gaip-witness
GAIP Witness Agent
io.github.tjcgraham-rgb/gaip-witness in the official MCP registry.
Endpoint https://www.gaipagents.com/mcp/agents/witness. Source: github.com/tjcgraham-rgb/gaip-agents.
The registry describes it as: Witness: agreed terms, delivery checks, signed receipts, dispute bundles and evidence packs.
We read its 23 tools on 2026-10-22. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
witness_register_terms witness_delivery gaip_receipt_export verify_gaip_receipt witness_dispute_bundle gaip_watch_register gaip_watch_list gaip_watch_remove gaip_watch_events gaip_citation_witness gaip_check_sar_receipt gaip_record_extract witness_accept_terms witness_finding witness_signoff assurance_prepare assurance_complete assurance_verify gaip_verify_supplier_claims inspect_counterparty_evidence gaip_evidence_pack gaip_incident_bundle gaip_measure_outcome_value
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-tjcgraham-rgb-gaip-witness)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.