AgentSec MCP
Security intelligence via x402 on Base. CVE lookup, IP reputation, secret scanning.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"agentsec-mcp": {
"url": "https://agentsec-mcp.agentsec-mcp.workers.dev/mcp"
}
}
}Remote endpoints
https://agentsec-mcp.agentsec-mcp.workers.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (3)
⚪cve_lookup
Look up known CVE vulnerabilities for an npm package+version or a specific CVE ID. Returns CVSS scores, descriptions, and fix versions from NVD and OSV. Results are cached for 10 minutes. Costs $0.01 USDC per call.
Input Schema
{
"type": "object"
}🟢reputation_check
Check the reputation of an IP address or domain using AbuseIPDB and VirusTotal. Returns a security verdict (malicious/suspicious/unknown/clean) with confidence signals. Verdict is conservative: incomplete data returns 'unknown' never 'clean'. Results are cached for 10 minutes. Costs $0.01 USDC per call.
Input Schema
{
"type": "object"
}🟢secret_scan
Scan text content for hardcoded secrets, API keys, and credentials using 20 pre-compiled patterns. Privacy guarantee: Input text is NEVER logged, cached, stored, or forwarded. Only findings_count and finding offsets (not matched values) are returned. Detected pattern types include: AWS keys, GitHub/GitLab PATs, OpenAI/Anthropic keys, Stripe secrets, Slack tokens, PEM private keys, JWT tokens, and 13 more. Per-call rate limit: 100/min. Payment: $0.05 USDC per scan.
Input Schema
{
"type": "object"
}Community
Evidence