AgentGuard — security checks for AI agents

io.github.shuaicongxiaomaiPublished by GitHub account shuaicongxiaomaiv0.1.2Updated Oct 24, 2026

Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Lets an assistant scan text and code for hard-coded secrets and check packages or dependency files for known CVEs.

What you can do
AgentGuard exposes three tools. scan_secrets flags hard-coded secrets such as API keys, tokens and private keys in text, code or diffs, running locally and returning only masked previews. check_cve reports whether a specific package version has known CVEs, with severity and fixed version. scan_dependencies reads a go.mod, package.json or requirements.txt and lists vulnerable pinned dependencies, capped at 200 per call.
When to use it
Useful when an agent writes, reviews or commits code and you want a quick secret check before content is logged or sent, or when you want to know whether a pinned dependency version has known vulnerabilities without leaving the assistant.
Requirements
Runs as a local stdio process on the user's machine; desktop only. Install via the Docker image, a Go install, or a prebuilt binary. No API key, account or environment variables are declared. check_cve and scan_dependencies need network access to the public OSV.dev API; scan_secrets works fully offline.
Before you install
scan_secrets reads the text, code or diffs you give it, though it returns only masked previews rather than raw values. check_cve and scan_dependencies send package names and versions to the third-party OSV.dev API. The server is read-only and does not modify files, but review what you pass to it before scanning.

Installation

In SourceWeft

  1. Open AgentGuard — security checks for AI agents in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AgentGuard — security checks for AI agents (MCP server)

A free, open-source, single-binary MCP server that gives any AI agent (Claude Desktop, Cursor, Claude Code, …) security checks in the loop:

ToolWhat it doesData source
scan_secretsFlags hard-coded secrets (API keys, tokens, private keys) in text/code/diffs before the agent commits, logs, or sends them. Runs locally; values are masked.local (regex + entropy)
check_cveWhether a specific package version has known CVEs, with severity + fixed version.OSV.dev (free)
scan_dependenciesScans a go.mod / package.json / requirements.txt and reports every vulnerable pinned dependency.OSV.dev (free)

No API key, no account, no telemetry. Everything runs locally except CVE lookups, which hit the free public OSV.dev API.

Install

Pick whichever fits your setup. All three give the same stdio MCP server.

Docker (no Go toolchain needed)

sh
docker run -i --rm ghcr.io/shuaicongxiaomai/agentguard:latest demo

MCP client config (mcpServers block in Claude Desktop / Cursor / Claude Code):

jsonc
{  "mcpServers": {    "agentguard": {      "command": "docker",      "args": ["run", "-i", "--rm", "ghcr.io/shuaicongxiaomai/agentguard:latest"]    }  }}

Go install

sh
go install github.com/shuaicongxiaomai/agentguard@latest
jsonc
{ "mcpServers": { "agentguard": { "command": "agentguard" } } }

Prebuilt binary

Download the archive for your OS/arch from the Releases page, extract it, and point the config command at the absolute path to the binary.

Build from source

sh
go build -o agentguard .          # append .exe on Windows

Three ways to run it

1. demo — see it work, zero config:

sh
agentguard demo

Runs all three tools on sample inputs and prints the results.

2. stdio (default) — local use; the MCP client launches the binary. No port; the client manages its lifecycle. Use any of the configs above, then ask your agent: "scan this for secrets", "is lodash 4.17.20 vulnerable?", "check my package.json for vulnerable deps."

3. serve — Streamable HTTP service on a port (for a hosted/remote server):

sh
agentguard serve :8080          # or set PORT=8080# health:   GET  http://host:8080/healthz# MCP URL:  POST http://host:8080/mcp   (clients connect to this URL)

Use stdio for local use; use serve when you want a hosted server users connect to by URL without installing anything.

Notes

  • scan_secrets runs locally and never returns raw secret values — only masked previews.
  • scan_dependencies caps at 200 deps per call and queries OSV concurrently.
  • check_cve / scan_dependencies need network access to OSV.dev; scan_secrets is fully offline.

License

MIT.

Source: README.md at commit 2fe4239

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts