"author:isaacbitran" matching MCP servers:

Enables an agent to verify every number in its answer against the tool outputs of the same session, storing recorded outputs and flagging fabricated values that no tool produced. It exposes check, record, and reset tools so agents can recompute, correct, or drop unvouched numbers before finalizing.

Connects any number of AI agents — Claude Code, Codex, or any MCP client — to one git-backed Markdown vault of shared team memory, exposing tools for briefings, search, reading, recent changes, sharing facts, transcripts, and urgent-item acknowledgments. Agent writes are queued and reviewed by a librarian model, then privacy-checked, linted, and committed as attributed git changes, so every agent reads the same current truth.