Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
A free, open-source, single-binary MCP server that gives any AI agent (Claude Desktop, Cursor, Claude Code, β¦) security checks in the loop:
| Tool | What it does | Data source |
|---|---|---|
scan_secrets | Flags 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_cve | Whether a specific package version has known CVEs, with severity + fixed version. | OSV.dev (free) |
scan_dependencies | Scans 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.
Pick whichever fits your setup. All three give the same stdio MCP server.
MCP client config (mcpServers block in Claude Desktop / Cursor / Claude Code):
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.
1. demo β see it work, zero config:
Runs all three tools on sample inputs and prints the results.
2. stdio (default) β 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 β Streamable HTTP service on a port (for a hosted/remote server):
Use stdio for local use; use serve when you want a hosted server users connect to by URL
without installing anything.
scan_secrets runs locally and never returns raw secret values β 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.MIT.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/agentguard-security-checks-for-ai-agents)<a href="https://allmcps.com/mcp/agentguard-security-checks-for-ai-agents"><img src="https://allmcps.com/api/badge/agentguard-security-checks-for-ai-agents?style=directory" alt="AgentGuard β security checks for AI agents on AllMCPs" /></a>