Agent Control Protocol: Admission Control for Agent Actions
Agent Control Protocol (ACP) is a formal technical specification for governance ofautonomous agents in B2B institutional environments. ACP is the admission controllayer between agent intent and system state mutation: before any agent action reachesexecution, it must pass a cryptographic admission check that validates identity,capability scope, delegation chain, and policy compliance simultaneously. ACP defines the mechanisms of cryptographic identity, capability-based authorization,deterministic risk evaluation, verifiable chained delegation, transitive revocation,and immutable auditing that a system must implement for autonomous agents to operateunder explicit institutional control. The v1.11 specification comprises 36 technical documents organized into five conformancelevels (L1-L5). It includes a Go reference implementation of 22 packages covering allL1-L4 capabilities, 42 signed conformance test vectors (Ed25519 + SHA-256), and anOpenAPI 3.1.0 specification for all HTTP endpoints. Specification and implementation: https://github.com/chelof100/acp-framework-en
Authors
- Marcelo Fernandez
Institutions
- Smile Train (US)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-03-17
- DOI
- https://doi.org/10.5281/zenodo.19072333
- Primary Topic
- Access Control and Trust
- Type
- article
- Field-Weighted Citation Impact
- 0.00