Skip to content
Back to the index

aegis-sandbox

PyPIInfrastructure

PulseGate's liveness check found it on 14 Sep 2026; it is registered on PyPI and has been in the index since 14 Sep 2026. How this is checked

Aegis Sandbox is an open-source Python package that acts as a policy proxy at the MCP layer. It applies security rules to agent interactions and maintains tamper-evident audit trails for developers operating AI agent systems.

Inferred · not functionally tested

Open SourceMITCLISelf-hostedAPI
Visit PyPI

Overview

5 features

Purpose: Preventing unsafe or unauthorized agent actions while preserving trustworthy audit records.

Inferred · not functionally tested

Audience: developers building AI agents and MCP integrations

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: indicated (inferred, not tested)

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

Constraint provenance is unknown; confirm requirements with the publisher.

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

aegis-sandbox is an AI security & guardrails project. Inferred · not functionally tested: It focuses on preventing unsafe or unauthorized agent actions while preserving trustworthy audit records. Inferred · not functionally tested: It is built as an open-source project for developers building AI agents and MCP integrations. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: aegis-sandbox is available on the command line and API, and it can be self-hosted.

aegis-sandbox first shipped in 2026. Inferred · not functionally tested: Among its 5 catalogued features are MCP proxy, policy enforcement, and audit trail. 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

  • MCP proxy
  • Policy enforcement
  • Audit trail
  • Tamper evidence
  • Agent security

Topics: Inferred · not functionally tested

Tags
mcp-policyagent-securityaudit-trailstamper-evident-logging

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
MCP
Runs on
CLISelf-hostedAPI-only

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tier

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed14 Sep · 23:23 UTC
    aegis-sandbox seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about aegis-sandbox

What is aegis-sandbox?
Inferred · not functionally tested: Aegis-sandbox focuses on preventing unsafe or unauthorized agent actions while preserving trustworthy audit records. It is catalogued under AI security & guardrails on PulseGate.
Who is aegis-sandbox for?
Inferred · not functionally tested: aegis-sandbox is an open-source project built for developers building AI agents and MCP integrations.
Is aegis-sandbox free?
Basis unknown · not verified: Yes — aegis-sandbox is open source under the MIT license and free to use.
What platforms does aegis-sandbox run on?
Basis unknown · not verified: aegis-sandbox runs on the command line and API. It can also be self-hosted.
Is aegis-sandbox still active?
PulseGate's liveness check found it on 14 Sep 2026.
When did aegis-sandbox launch?
aegis-sandbox first shipped in 2026.
Is aegis-sandbox open source?
Basis unknown · not verified: Yes — aegis-sandbox is open source under the MIT license.
Does aegis-sandbox have an API or integrations?
Inferred · not functionally tested: Yes — aegis-sandbox exposes an MCP server.

Similar projects

Closest matches by what these projects do