mcpbeat Sign in

Agentguard MCP Server

local only

Agentguard runs on your own machine — the client starts it, so there is no endpoint to ping. 40 installs a week from npm. Last commit 13 Jun 2026.

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

Installs per day peak 10 · avg 3 · +122% w/w
a month agotoday
40
Installs / week
npm · @mukundakatta/agentguard-mcp
1
Stars
0 open issues
13 Jun 2026
Last commit
no releases in 90 days
MIT
License
JavaScript

Nothing serious here today

Today is the operative word: we check Agentguard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

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.

run in your terminal
claude mcp add agentguard -- npx -y @mukundakatta/agentguard-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "agentguard": {
      "command": "npx",
      "args": [
        "-y",
        "@mukundakatta/agentguard-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.agentguard]
command = "npx"
args = ["-y", "@mukundakatta/agentguard-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "agentguard": {
      "command": "npx",
      "args": [
        "-y",
        "@mukundakatta/agentguard-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "agentguard": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@mukundakatta/agentguard-mcp"
      ]
    }
  }
}

Alternatives to Agentguard

same job, measured the same way
Agent Guardrail
by rudimentall1

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

118 installs/wk local only
Agent Trust Firewall
by benji18sport

Free pre-action policy checks and data cleaning for autonomous AI agents.

5 tools answering
Mnki MCP
by mnkiagentos

MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.

77 installs/wk local only
Gnt
by gnt-ai

Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.

answering
agent-custody
by svayatta

MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt

1 236 installs/wk local only
MCP Output Firewall
by tangfei7777-cell

Three-layer firewall for MCP: content, egress and action policy. Proxy or server.

42 installs/wk local only
Agent Spend Policy MCP
by dingdawg

Local agent spend-policy checks. No funds, keys, payment authority, or network access.

50 installs/wk local only
Shrike
by shrike-security

Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.

332 installs/wk local only

Agentguard — questions

Answers built from our own checks of this server.

Why is there no uptime for Agentguard?
Agentguard 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 npm package @mukundakatta/agentguard-mcp was installed 40 times last week.
How do I connect Agentguard?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @mukundakatta/agentguard-mcp straight from npm; nothing to host, nothing to sign up for.
How many people use Agentguard?
The npm package @mukundakatta/agentguard-mcp was installed 40 times in the last week. Week over week that is +122%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Agentguard open source?
Yes — it is published under the MIT licence, written in JavaScript 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.