MCP Servers

Acacian/aegis

Name: Acacian/aegis
Author: Various

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD.

Visit site ↗

Our verdict

Not reviewed yet

We have not reviewed Acacian/aegis yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Acacian/aegis

Acacian/aegis is an LLM guardrails and prompt injection detection library for Python. It auto-instruments LangChain, CrewAI, OpenAI, LiteLLM, and eight other frameworks with a single line of code, providing PII masking, toxicity detection, and policy CI/CD without code changes.

Best for

Python developers who need to add basic safety controls to existing LLM applications quickly

Use cases

Integrate prompt injection detection into LangChain agents
Add PII masking to OpenAI API calls
Automate policy enforcement for LLM outputs in CI/CD

Notes

9 stars on GitHub. Last updated 2026-05-05. Licensed MIT.

Pros

Minimal integration effort with one-line setup
Supports a wide range of popular LLM frameworks
Combines multiple guardrails (injection, PII, toxicity) out of the box

Cons

Python-only, limiting use in polyglot stacks
May introduce latency overhead during inference
Requires familiarity with guardrail configuration for custom policies

Key facts

What we have checked

Days since the last commit: 10; Checked 26 Oct 2026GitHub
GitHub forks: 5; Checked 26 Oct 2026GitHub
GitHub stars: 18; Checked 26 Oct 2026GitHub
Days to a first reply on issues: 219.7; Checked 26 Oct 2026GitHub
Open issues: 4; Checked 26 Oct 2026GitHub
Releases in the last 90 days: 1; Checked 26 Oct 2026GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

How to use

How to set it up

As the listing publishes it. We have not run this install.

Install

pip install agent-aegis

Clients the listing names (not checked here)

Claude Desktop, Cursor, Windsurf, VS Code, ChatGPT

Install

Add Acacian/aegis to your client

Not verified yet

Our lab has not run this server yet. "Config checked" on a client means the recipe matches that client's documented config format; it does not mean we ran it.

Claude Code

Config checked

Run in your terminal (runs on your computer)

claude mcp add --transport stdio acacian-aegis -- uvx agent-aegis@0.1.6

Version 0.1.7 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Claude Code's config docs

Claude Desktop

Config checked

Add to claude_desktop_config.json (runs on your computer)

{
  "mcpServers": {
    "acacian-aegis": {
      "command": "uvx",
      "args": [
        "agent-aegis@0.1.6"
      ]
    }
  }
}

Version 0.1.7 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Claude Desktop's config docs

Cursor

Config checked

Add to .cursor/mcp.json (runs on your computer)

{
  "mcpServers": {
    "acacian-aegis": {
      "command": "uvx",
      "args": [
        "agent-aegis@0.1.6"
      ]
    }
  }
}

Version 0.1.7 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Cursor's config docs

VS Code

Config checked

Add to .vscode/mcp.json (runs on your computer)

{
  "servers": {
    "acacian-aegis": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agent-aegis@0.1.6"
      ]
    }
  }
}

Version 0.1.7 · From the Official MCP registry, read 24 Oct 2026 · Format checked against VS Code's config docs

Codex

Config checked

Add to ~/.codex/config.toml (runs on your computer)

[mcp_servers.acacian-aegis]
command = "uvx"
args = ["agent-aegis@0.1.6"]

Version 0.1.7 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Codex's config docs

ChatGPT: ChatGPT connects only to remote servers that need no API key.

Recipes come from the server's entry in the official MCP registry. Check the package name before you run it, and keep keys out of shared files.

Works with

What Acacian/aegis connects to

5 clients, each with how we know and when we checked.

Works with	Type	How we know	Checked
Claude Code	Client	Install recipe matches the client's documented formatRuns locally, version 0.1.7Config checked	24 Oct 2026Claude Code docs
Claude Desktop	Client	Install recipe matches the client's documented formatRuns locally, version 0.1.7Config checked	24 Oct 2026Claude Desktop docs
Cursor	Client	Install recipe matches the client's documented formatRuns locally, version 0.1.7Config checked	24 Oct 2026Cursor docs
VS Code	Client	Install recipe matches the client's documented formatRuns locally, version 0.1.7Config checked	24 Oct 2026VS Code docs
Codex	Client	Install recipe matches the client's documented formatRuns locally, version 0.1.7Config checked	24 Oct 2026Codex docs

Health and security

Is Acacian/aegis looked after, and what do its setup files show

Health score

38 out of 100

Does someone look after this repository? It does not say the code is good or safe. Worked out from GitHub signals checked 26 Oct 2026. How it is worked out

Part	Points	What we saw
Recent activity	30 of 30	Last push 10 days ago
Releases	7.5 of 15	1 release in 90 days
Issue replies	0 of 20	First reply in 219.7 days (median)
Maintainer	0 of 15	Owned by a single user
Official source	0 of 20	Community server

Sources

Where this comes from

GitHubRegistry
Checked 26 Oct 2026 · Days since the last commit, GitHub forks, GitHub stars, Days to a first reply on issues, Open issues, Releases in the last 90 days

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

Uses2 entries

PAppslowCatalogue

LangChain

Various

LangChain provides the engineering platform and open source frameworks developers use to build, test, and deploy reliable AI agents.

Source reviewedOOSS

LiteLLM

BerriAI

A Python SDK and a self-hosted proxy, the LiteLLM AI Gateway, that let apps call more than 100 model providers through one OpenAI-format API, with virtual keys, budgets, fallbacks and spend tracking.

★ 48,950

Works in1 entry

AAgentslowCatalogue

Crewai

Community

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

★ 55,300

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

← Back to MCP Servers Submit your own entry →