PCP v0.1: A Draft Protocol for Purpose-Bound, Revocable AI Agent Authority
sierracatalina · x · 2026-09-18
Developer sierracatalina released Personal Context Protocol (PCP) v0.1 on GitHub: a draft authority contract for AI agents that makes actions purpose-bound, scoped, expiring, revocable, and budgeted.
Key design: a PCP grant specifies the issuing principal and the acting principal/agent/device, one exact purpose and audience, allowed actions and resources, optional integer budget limits, a bounded time window with revocation family, and whether constrained subdelegation is allowed. The protocol stresses that identity, transport auth, discovery metadata, and context access never create authority by themselves.
The repo ships machine-readable schemas, a deterministic reference model, tests, and integration profiles — no live issuer or production service yet.
More from coding & agent
- Pydantic AI agents now run on TypeSafe's Jev with per-field confidence outputs — Paimaamu · 2026-09-18
- Demo: GPT-6 Astra edits video in DaVinci via MCP at impressive speed — toolstelegraph · 2026-09-18
- After a day with Jev: a blazing-fast classifier, not a GPT replacement — jiayuan_jy · 2026-09-18
- Wiring Claude Code, Codex and Cursor to one shared MCP memory server — Asly97 · 2026-09-18
- Running Claude Code, Codex and Cursor on One Project: How I Finally Stopped Losing Context — Asly97 · 2026-09-18
- Multica hits 50k GitHub stars, ships cloud agent integration with Qoder — jiayuan_jy · 2026-09-18