tool-call-guard
PulseGate's liveness check found it on 14 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 4 Aug 2026. How this is checked
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.
Inferred · not functionally tested
Overview
6 featuresPurpose: Safely controlling and auditing which tools AI agents are allowed to call without risking unintended or malicious actions.
Inferred · not functionally tested
Audience: developers
Inferred · not functionally tested
Functions: agents, monitoring
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: unknown
Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
tool-call-guard is an AI security & guardrails project. Inferred · not functionally tested: Safely controlling and auditing which tools AI agents are allowed to call without risking unintended or malicious actions. Inferred · not functionally tested: tool-call-guard is an open-source project aimed at developers. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: 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. Inferred · not functionally tested: Key capabilities include Deny-by-default Policy, allowlists, and Argument Validation. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Deny-by-default Policy
- Allowlists
- Argument Validation
- Rate Caps
- Human Approval Hooks
- Dry-run Mode
Topics: Inferred · not functionally tested
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed4 Aug · 21:32 UTCtool-call-guard seen via PyPI Bulk EnumeratorSource: PyPI Bulk Enumerator · Open
Frequently asked questions about tool-call-guard
- What does tool-call-guard do?
- Inferred · not functionally tested: Safely controlling and auditing which tools AI agents are allowed to call without risking unintended or malicious actions. It is catalogued under AI security & guardrails on PulseGate.
- Who is tool-call-guard for?
- Inferred · not functionally tested: tool-call-guard is an open-source project built for developers.
- Is tool-call-guard free?
- Basis unknown · not verified: Yes — tool-call-guard is open source under the MIT license and free to use.
- What platforms does tool-call-guard run on?
- Basis unknown · not verified: tool-call-guard runs on the command line and API.
- Is tool-call-guard still maintained?
- PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 3 commits in the last 90 days.
- What are alternatives to tool-call-guard?
- Similar projects tracked by PulseGate include jig-toolguard, toolgate-ai, and Gatekeeper.jig-toolguardtoolgate-aiGatekeeper
- Who makes tool-call-guard?
- tool-call-guard is developed by Binay Dhakal.
- When did tool-call-guard launch?
- tool-call-guard first shipped in 2026.
Similar projects
Closest matches by what these projects do