agentmods.dev

dfx-agentguard

dfx-agentguard is an MCP server for Claude Code, Codex, Cursor from dockfixlabs/agentguard. Its token cost is not measured, scanned A, original, LGPL-3.0.

A locally run security scanner for AI agents, delivered as a Python package.

In plain words
What is it for?
It is for detecting prompt injection, tool abuse, data theft, and risks from the OWASP ASI Top 10 list, a set of common security risks for AI systems.
Why use it?
It looks for attacks and unsafe agent behavior that could cause tools to be misused or information to leave the system.

MCP server for Claude CodeCodexCursor

not rated 1 1mo ago A scan tokens not measured LGPL-3.0
View the source file dockfixlabs/agentguard
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.

agentmods
npx agentmods add mcp/dockfixlabs/agentguard/dfx-agentguard
Clone the repo
git clone --depth 1 https://github.com/dockfixlabs/agentguard

Made for: Claude Code, Codex, Cursor.

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 dfx-agentguard

README.md
[![agentmods](https://agentmods.dev/badge/mcp/dockfixlabs/agentguard/dfx-agentguard.svg)](https://agentmods.dev/mcp/dockfixlabs/agentguard/dfx-agentguard)
Your own site
<a href="https://agentmods.dev/mcp/dockfixlabs/agentguard/dfx-agentguard"><img src="https://agentmods.dev/badge/mcp/dockfixlabs/agentguard/dfx-agentguard.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. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

dfx-agentguard 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 3d 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.

listed in the official MCP registry · 8 lines

The source is not reproduced here

Licensed LGPL-3.0

The repository is licensed LGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 3d ago First seen · 8 lines scan A 3b93a9cc6c6c

Subscribe to this mod's changes

dfx-agentguard is an MCP server published in the GitHub repository dockfixlabs/agentguard (1 stars, last pushed 1mo ago), licensed LGPL-3.0. 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.

Building agentsPrompt InjectionSecurityagent-securityai-securityllm-securityowaspstatic-analysis
Related

Other mcp servers, from other repositories

docs

MCP server "docs", hosted remotely at docs.example.com, as configured in meghal86/promptsonar.

meghal86/promptsonar · not measured

shellward

AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP. Runs locally from the shellward npm package. Needs 3 environment variables to run.

jnMetaCode/shellward · not measured

mcp-safeguard

Security scanner for MCP servers — detect prompt injection, credential leaks, exposed endpoints, tool poisoning, and source-level credential-handling flaws. Runs locally from the mcp-safeguard Python package.

SyedAnas01/mcp-safeguard · not measured

sentinel-scan-cli

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics. Runs locally from the sentinel-scan-cli npm package.

Ventrova/sentinel-scan-cli · not measured

malskanner

Scan a repo for hidden prompt-injection payloads before your AI agent trusts it. Runs locally from the malskanner npm package.

Octolabo/malskanner · not measured

github

MCP server "github" as configured in arshan846/pluto-aguard. Runs in Docker (ghcr.io/github/github-mcp-server). Needs 1 environment variable to run.

arshan846/pluto-aguard · not measured