Skip to content
Back to the index

AIAgentFirewall

PyPIInfrastructure

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

AIAgentFirewall is a Python package and CLI tool that acts as a security firewall for AI agents, skills, and MCP servers. It scans packages before installation to detect prompt injection, malicious behavior, and supply-chain risks. Licensed under MIT and hosted on GitHub, it is designed for developers building with or deploying AI agents who need to protect their systems from untrusted components.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

4 features

Purpose: Safely evaluating and installing untrusted AI agents, skills, and MCP servers without exposing systems to prompt injection or supply-chain attacks.

Inferred · not functionally tested

Audience: developers

Inferred · not functionally tested

Functions: data_extraction

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

AIAgentFirewall sits in PulseGate's AI & LLM security category. Inferred · not functionally tested: Safely evaluating and installing untrusted AI agents, skills, and MCP servers without exposing systems to prompt injection or supply-chain attacks. Inferred · not functionally tested: AIAgentFirewall is an open-source project aimed at developers. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

Behind AIAgentFirewall is mmedabo, and it first shipped in 2026. Inferred · not functionally tested: Key capabilities include Security Scanning, Prompt Injection Protection, and Supply Chain Security. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Security Scanning
  • Prompt Injection Protection
  • Supply Chain Security
  • AI Agent Firewall

Topics: Inferred · not functionally tested

Tags
ai-agent-securitymcp-firewallprompt-injection-scannersupply-chain-security

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
MCP
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHub

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed4 Aug · 07:46 UTC
    AIAgentFirewall seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about AIAgentFirewall

What is AIAgentFirewall?
Inferred · not functionally tested: Safely evaluating and installing untrusted AI agents, skills, and MCP servers without exposing systems to prompt injection or supply-chain attacks. It is catalogued under AI & LLM security on PulseGate.
Who should use AIAgentFirewall?
Inferred · not functionally tested: AIAgentFirewall is an open-source project built for developers.
Is AIAgentFirewall free?
Basis unknown · not verified: Yes — AIAgentFirewall is open source under the MIT license and free to use.
What platforms does AIAgentFirewall run on?
Basis unknown · not verified: AIAgentFirewall runs on the command line. It can also be self-hosted.
Is AIAgentFirewall still active?
PulseGate's liveness check found it on 14 Sep 2026.
What are alternatives to AIAgentFirewall?
Similar projects tracked by PulseGate include ai-firewall-mcp, inter-agent-guard, and Agent Scan.ai-firewall-mcpinter-agent-guardAgent Scan
Who develops AIAgentFirewall?
AIAgentFirewall is developed by mmedabo.
When did AIAgentFirewall launch?
AIAgentFirewall first shipped in 2026.

Similar projects

Closest matches by what these projects do