An MCP server for building and managing AI agents with policy enforcement and compliance checks. It runs locally and uses two configuration values.

Creating and managing policy-compliant AI agents and checking whether their actions meet configured rules.

It helps apply safety and compliance requirements while agents are created or managed.

agentos — MCP server for Claude Code and Codex by imran-siddique

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/imran-siddique/agent-os

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/imran-siddique/agent-os/mcp-server-agentos.svg)](https://agentmods.dev/mcp/imran-siddique/agent-os/mcp-server-agentos)

Your own site

<a href="https://agentmods.dev/mcp/imran-siddique/agent-os/mcp-server-agentos"><img src="https://agentmods.dev/badge/mcp/imran-siddique/agent-os/mcp-server-agentos.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agentos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

extensions/mcp-server/server.json · 13 lines

What it actually says

{
  "agentos": {
    "command": "npx",
    "args": [
      "-y",
      "agentos-mcp-server"
    ],
    "env": {
      "AGENTOS_POLICY_MODE": "",
      "AGENTOS_LOG_LEVEL": ""
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 13 lines scan A ef53eaf58b0d

Subscribe to this mod's changes

agentos is an MCP server published in the GitHub repository imran-siddique/agent-os (74 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

AI Safety Building agents LLM Legal and compliance agent-framework ai-agents policy-engine

rail-score

Responsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP. Remote server at mcp.responsibleailabs.ai.

Responsible-AI-Labs/rail-score-mcp · not measured

openaccountants-mcp

MCP server for OpenAccountants tax skills. Runs locally from the openaccountants-mcp Python package.

openaccountants/openaccountants · not measured

aegis

Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes. Runs locally from the agent-aegis Python package. Needs 1 environment variable to run.

Acacian/aegis · not measured

agentos