Kernel-Level MCP Governance
Arxiv
pdf
2026-04-01T00:00:00
arXiv Paper — PDF not available.
Only the Executive Summary is available here. To read or download the full paper, visit the
arXiv abstract page.
Abstract
AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agents' 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, companion paper). The gateway interposes on every MCP tool call in a 6-layer pipeline: schema validation, trust tier check, rate limit, adversarial pre-filter, ProbeLogits gate (the load-bearing semantic check), and constitutional policy match, with a Blake3-hashed audit chain.
Loading executive summary...