Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives
AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls: privileged operations with side effects on shared state, yet today's safety enforcement lives entirely in userspace, where a 10-line script can bypass it. I propose Governed MCP, a kernel-resident tool governance gateway built on a logit-based safety primitive (ProbeLogits). The gateway interposes on every MCP tool call in a 6-layer pipeline
Record details
Published: 18 April 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs
arXiv · 17 April 2026
Consent Chain Degradation in Embodied Multi-Agent Systems: Bridging the Gap Between AI Agent Governance and Robot Ethics
arXiv · 17 April 2026
Governance by Design: Architecting Agentic AI for Organizational Learning and Scalable Autonomy
arXiv · 17 April 2026
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
arXiv · 17 April 2026
From Admission to Invariants: Measuring Deviation in Delegated Agent Systems
arXiv · 19 April 2026
PolicyBank: Evolving Policy Understanding for LLM Agents
arXiv · 16 April 2026
How to cite this record
ethics.ai (18 April 2026), “Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives,” evidence record 5697, https://ethics.ai/record/5697 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.