MCP.Market

Aegis — AI Agent Governance MCP server

by Acacian·io.github.Acacian/aegis·v0.1.7·17 stars
No reviews yet

Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

17 stars104 downloads/wk

Reviews

Write one

Nobody has reviewed Aegis — AI Agent Governance yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Aegis — AI Agent Governance tools (5, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_risk

    Quick risk check for an action type + target combination.

  • evaluate_action

    Evaluate an AI agent action against the current governance policy.

  • evaluate_batch

    Evaluate multiple actions at once against the governance policy.

  • get_policy

    Get the current governance policy rules.

  • update_policywrite action

    Hot-reload the governance policy from a YAML string.

Public scan report

scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan64 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 29 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Aegis — AI Agent Governance compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
5
the typical AI and agents server has 6
Tools that change things
20%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
17
more than 88% of 2,711 AI and agents servers
Downloads a week
104
more than 65% of 1,538 AI and agents servers with a package

What its tools let an agent do: 2 read · 1 change · 2 run or deploy

Install Aegis — AI Agent Governance in Claude Code, Cursor or VS Code

claude mcp add aegis -- uvx agent-aegis
Add to Cursor

What the publisher says

From the Aegis — AI Agent Governance repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.Acacian/aegis --> Agent-Aegis The governance layer for AI agents. One API, 12 frameworks, every governance primitive. Aegis is to agent governance what Redis is to data structures — one runtime that unifies prompt-injection blocking, PII masking, policy enforcement, trust delegation, and tamper-evident audit across every agent framework. No code changes. pip install agent-aegis → aegis.auto_instrument() → 12 frameworks are now governed.

What is Aegis &bull; Primitives &bull; Frameworks &bull; Use Cases &bull; 30-Second Start &bull; Research &bull; Docs &bull; Playground

English &bull; 한국어

What is Aegis

Every AI agent framework reinvents the same governance primitives — and each one does it slightly differently. Aegis is the abstraction layer that unifies them.

import aegis
aegis.auto_instrument()    # 12 frameworks governed. No other code changes.

You don't write a LangChain guardrail and a CrewAI guardrail and an OpenAI guardrail — you write one Policy and every framework inherits it.

How this differs from the guardrail libraries

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Aegis — AI Agent Governance: common questions

Is Aegis — AI Agent Governance MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Aegis — AI Agent Governance safety report
How do I install Aegis — AI Agent Governance?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Aegis — AI Agent Governance need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Aegis — AI Agent Governance maintained?
The last commit was 67 days ago (2026-08-29). The latest release is v0.1.7.
What can I use instead of Aegis — AI Agent Governance?
Servers from other publishers that do the same job: HOL Guard MCP server, Emilia Protocol MCP server and Roast My Design System MCP server.
How does Aegis — AI Agent Governance compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Aegis — AI Agent Governance

Same job from other publishers: the closest match first, then the best rated.

  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Roast My Design System
    Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
    A
  • Decionis Commerce Gate MCP
    Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors.
    A
  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A