Mcp-Security on CuraSec

toolfence: fail-closed policy enforcement for MCP tool calls

Fri, 28 Aug 2026 21:21:40 +0000

Engineer — Learn: If you run MCP-based agent workflows, toolfence offers a local, fail-closed approval layer worth evaluating — no exploitation pressure, just a new defensive primitive to assess against your AI toolchain.
SOC/IR — Skip
Leader — Learn: Signals growing tooling demand around AI agent access control; useful context if your organization is drafting policy for MCP or agentic AI use before formal controls exist.

Wed, 26 Aug 2026 11:42:13 +0000

Engineer — Plan: Teams using Marimo in AI/ML workflows should update to the patched version; the attack surface (opening a crafted notebook in edit mode triggers a local subprocess via MCP) is a real supply-chain-style risk, but no KEV listing, public PoC, or active exploitation signals mean this isn’t an emergency patch.
SOC/IR — Skip
Leader — Skip

Mon, 24 Aug 2026 13:10:29 +0000

Engineer — Learn: Introduces a concrete attack class against MCP-based agent systems — agents can be induced to request excessive resources across modalities, causing DoS-like degradation. No exploitation in the wild; worth reviewing AEGIS’s OPA-based policy model if you’re building or operating MCP tool servers.
SOC/IR — Skip
Leader — Skip

Mon, 27 Jul 2026 15:10:27 +0000

Engineer — Learn: Academic research presenting a declarative vetting-plus-runtime authorization approach for LLM agent tools using Answer Set Programming; no shipping implementation to adopt today, but the pre-admission characterization pipeline (syscall tracing, mock execution, source analysis) is a useful design reference for teams building or auditing agentic systems with third-party MCP-style tools.
SOC/IR — Skip
Leader — Learn: Provides early framing on a governance gap — third-party tool risk in LLM agent deployments — that will become a vendor-risk and audit question as agentic AI adoption grows; no immediate action but useful input for shaping an AI agent usage policy before it’s needed.