agentmods.dev

agentguard47

agentguard47 is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from bmdhodl/agent47. Its token cost is not measured, scanned A, original, MIT.

A read-only MCP server for viewing coding-agent traces, alerts, costs, usage, and budget health. It runs locally and connects to the AgentGuard service using an API key and URL.

In plain words
What is it for?
Use it to inspect agent activity, warnings, usage, costs, and remaining budget.
Why use it?
It gives an agent access to operational and spending information without allowing it to change that information.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 4repo today A scan tokens not measured original MIT

Good fit Use it to inspect agent activity, warnings, usage, costs, and remaining budget.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/bmdhodl/agent47/agentguard47
View source ↗ bmdhodl/agent47 agentguard47.com
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/bmdhodl/agent47

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.

agentmods badge for agentguard47

README.md
[![agentmods](https://agentmods.dev/badge/mcp/bmdhodl/agent47/agentguard47/github.svg)](https://agentmods.dev/mcp/bmdhodl/agent47/agentguard47)
Your own site
<a href="https://agentmods.dev/mcp/bmdhodl/agent47/agentguard47"><img src="https://agentmods.dev/badge/mcp/bmdhodl/agent47/agentguard47/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agentguard47

Your own site · 80×15
<a href="https://agentmods.dev/mcp/bmdhodl/agent47/agentguard47"><img src="https://agentmods.dev/badge/mcp/bmdhodl/agent47/agentguard47.svg" alt="Reviewed on agentmods" width="80" 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

agentguard47 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 1mo 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.

mcp-server/server.json · 13 lines

What it actually says

{
  "agentguard47": {
    "command": "npx",
    "args": [
      "-y",
      "@agentguard47/mcp-server"
    ],
    "env": {
      "AGENTGUARD_API_KEY": "",
      "AGENTGUARD_URL": ""
    }
  }
}
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.

  1. 1mo ago First seen · 13 lines scan A 48698391821a

Subscribe to this mod's changes

agentguard47 is an MCP server published in the GitHub repository bmdhodl/agent47 (4 stars, last pushed today), 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 2026-08-31.

AI SafetyAnalytics and metricsGuardrailsLangChainai-agentsanthropicdeveloper-tools
Related

Other mcp servers, from other repositories

qorami

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection. Runs locally from the qorami-mcp npm package. Needs 1 environment variable to run.

loicfontaine-max/qorami-sdk · not measured

agentsgate

AI Agent I/O Tracking & Rollback System — MCP Proxy Gateway. Runs locally from the agentsgate npm package.

agentsgate/agentsgate · not measured

sentinel-ai

MCP server "sentinel-ai" as configured in MaxwellCalkin/sentinel-ai. Runs sentinel.mcp_server with python.

MaxwellCalkin/sentinel-ai · not measured

shield

MCP server "shield" as configured in kobepaw/goop-shield-community. Launched with goop-shield mcp --port 8787.

kobepaw/goop-shield-community · not measured

reference-langchain

MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

thumbgate

MCP server "thumbgate" as configured in IgorGanapolsky/ThumbGate. Runs adapters/mcp/server-stdio.js with node.

IgorGanapolsky/ThumbGate · not measured