Tool-call-guard is a lightweight, framework-agnostic Python library that acts as a security gate for AI agent tool calling. It implements a deny-by-default policy with configurable allowlists, argument validation, rate limiting, human-approval workflows, dry-run simulation, and a full audit trail. The package has zero dependencies and is distributed under the MIT license.
tool-call-guard is a Developer Tools project. Safely controlling and auditing which tools AI agents are allowed to call without risking unintended or malicious actions. tool-call-guard is an open-source project aimed at developers. The project is open source (MIT). It ships for the command line and API.
Binay Dhakal builds and maintains tool-call-guard, and it first shipped in 2026. The project is developed in the open on GitHub with 3 commits in the last 90 days. Key capabilities include Deny-by-default Policy, allowlists, and Argument Validation. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do