Glossary

org_context_lookup — MCP tool for org-wide de-dup

**org_context_lookup** is the GenZAgents MCP tool that queries the org's receipt pool at the start of every new conversation. Surfaces matches: "Carlos did this on May 3rd — see receipts rcpt_…". Eliminates redundant AI work.
Open spec on GitHubInstall MCP server

How it fires

The MCP server instructs the model to call org_context_lookup with the first user prompt. The lookup runs hybrid lexical + semantic search against the org's receipt pool.

Hit rate over time

Day 1: ~0% (no past receipts). Day 30: ~5%. Day 90: ~18% as the receipt pool grows. The de-dup value compounds as the institutional memory grows.

Privacy

Respects per-project ACLs. Confidential projects don't surface in lookups for unauthorized users.

Latency

~120ms — added at conversation start, below the user-perceptible threshold.

Related

restore_chat

The MCP tool that returns a portable manifest, letting AI work move across providers.

work receipt

A signed JSON record of AI-mediated work. Ed25519 signature over JCS-canonical JSON.

MCP tool

A typed function exposed by an MCP server to AI hosts. Has a schema; can be invoked by the model.

Get the trust layer for your AI work

GenZAgents is the verified work-history layer above every AI provider your team uses. Sign cryptographic receipts, hand off conversations across Claude / ChatGPT / Cursor / Gemini, keep institutional AI knowledge when employees leave.

Join the launch waitlistInstall MCP server

Last reviewed · 2 min read· Open spec· Changelog