What it does
Agent Toolbox is an MCP server with 26 pre-action safety gates for AI agents. Each gate is deterministic, runs offline and returns a signed verdict.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Agent Toolbox
26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.
v0.1.4As shown on registry.modelcontextprotocol.io when we last read it