Autonomous agents can produce harmful behavioral patterns from individually valid requests — a threat class that per-request policy evaluation cannot address, because stateless engines evaluate each request in isolation and cannot enforce properties that depend on execution history. We present ACP, a temporal admission control protocol that enforces behavioral properties over execution traces by combining static risk scoring with stateful signals (anomaly accumulation, cooldown) through a LedgerQuerier abstraction separating decision logic from state management. ACP is not an anomaly detection system: it does not detect suspicious patterns and alert; it blocks execution based on deterministic, history-aware risk scoring, providing a hard enforcement boundary rather than an advisory signal. Key results: - Under a 500-request workload where every request is individually valid (RS=35), a stateless engine approves all 500 requests, while ACP limits autonomous execution to 2 out of 500 (0.4%), escalating after 3 actions and enforcing denial after 11. - Decision evaluation runs at 739–832 ns (p50); throughput reaches 1,720,000 req/s (baseline) and 920,000 req/s at 10 concurrent workers. - Safety and liveness properties are model-checked via TLA+ (11 invariants + 4 temporal properties, 0 violations); two-agent safety verified across 4,294,930,695 distinct states with zero violations. - Runtime correctness validated by 73 signed conformance test vectors. - We identify and formalize deviation collapse — a governance failure mode in which enforcement is active but never exercised — and introduce Boundary Activation Rate (BAR) as its detection mechanism. - ACP-RISK-3.0 eliminates cross-context interference by scoping rate-based anomaly signals via PatternKey(agentID, capability, resource). ACP is Paper 1 of a 6-paper Agent Governance Series: P0 — Atomic Decision Boundaries (structural impossibility of split evaluation systems). P2 — Behavioral drift detection via the Invariant Measurement Layer (IML). P3/4 — Governance structure: fair multi-agent allocation, strategy-proofness, and compositional irreducibility (consolidated paper). P5 — Runtime execution validity under partial observability (RAM). P6 — Operationalization of RAM as a runtime enforcement protocol. All companion papers are published on Zenodo. Specification and implementation: https://github.com/chelof100/acp-framework-en Full series (Agent Governance Series, Papers 0–6): P0 — Atomic Decision Boundaries: https://doi.org/10.5281/zenodo.19670649 | arXiv:2604.17511 P1 — Agent Control Protocol (ACP, this paper): https://doi.org/10.5281/zenodo.19672575 | arXiv:2603.18829 P2 — From Admission to Invariants (IML): https://doi.org/10.5281/zenodo.19672589 | arXiv:2604.17517 P3/4 — Irreducible Governance Structure (consolidated): https://doi.org/10.5281/zenodo.19708496 P5 — Reconstructive Authority Model (RAM): https://doi.org/10.5281/zenodo.19669430 | arXiv:2604.22898 P6 — Operationalizing Reconstructive Authority: https://doi.org/10.5281/zenodo.19699460