Agent Guardrail MCP Server

by rudimentall1 Your server? Claim it

local only

Agent Guardrail runs on your own machine — the client starts it, so there is no endpoint to ping. 168 installs a week from pypi. Last commit 22 Sep 2026.

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Installs per day peak 39 · avg 17 · +56% w/w

a month agotoday

168

Installs / week

pypi · guardrail-mcp

Stars

0 open issues

22 Sep 2026

Last commit

from GitHub

MIT

License

Python

What the code does

We read the source, 1 d ago · rules ccca72095570

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Page executes code built at runtime landing/index.html:484

        output.innerHTML = data.output.map(l => `<div>${l}</div>`).join("");

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-guardrail -- uvx guardrail-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-guardrail": {
      "args": [
        "guardrail-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.agent-guardrail]
command = "uvx"
args = ["guardrail-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "agent-guardrail": {
      "args": [
        "guardrail-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "agent-guardrail": {
      "args": [
        "guardrail-mcp"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to Agent Guardrail

same job, measured the same way

signet-eval

by jmcentire

Deterministic policy enforcement and MCP management for AI agent tool calls.

local only

Delentia Sovereign AI Operating System

by delentia-labs

Stop rogue AI-agent tool calls before they run: deterministic policy gate + audit digest.

56 installs/wk local only

HumanMirror Forge

by humanmirror

Five deterministic micro-tools for AI-agent data pipelines: clean, dedupe, normalize, score, detect.

5 tools answering

Agent Core

by kinbinghua-lgtm

Deterministic computation tools for AI agents. Zero dependencies, no network, read-only.

38 installs/wk local only

Scout Security

by varpost

Deterministic, zero-token security scanner your AI agent calls to find and re-verify issues.

103 installs/wk local only

Agentguard

by mukundakatta

Network-egress firewall for agent tools: check URLs against a declarative policy.

28 installs/wk local only

Mandateguard

by ezequiellich44-cmd

Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.

local only

Aegis — AI Agent Governance

by acacian

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

324 installs/wk local only

Agent Guardrail — questions

Answers built from our own checks of this server.

Why is there no uptime for Agent Guardrail?

Agent Guardrail runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package guardrail-mcp was installed 168 times last week.

How do I connect Agent Guardrail?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls guardrail-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Agent Guardrail?

The pypi package guardrail-mcp was installed 168 times in the last week. Week over week that is +56%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agent Guardrail open source?

Yes — it is published under the MIT licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.