cve_search
Search NIST NVD CVE database by keyword, CVE ID, or severity. Returns CVE ID, description, CVSS score, affected products, references.
What is cve_search?
cve_search is a paid MCP tool in the Security category on agenttoll.dev. It costs $0.02 per call, settled in USDC on Base via the x402 payment protocol. No API keys, no accounts — your agent discovers it via /.well-known/agent.json, calls it, pays the $0.02 fee, and receives structured JSON.
Input parameters
{
"keyword": "optional search term",
"cve_id": "optional e.g. CVE-2024-1234",
"severity": "optional: LOW, MEDIUM, HIGH, CRITICAL"
}
Example usage
{
"keyword": "log4j"
}
HTTP endpoint
POST to this path with JSON body. Server returns 402 with x402 payment requirements.
/paid/security/cve-search
How to call cve_search
Connect any MCP-compatible client (Claude Desktop, Cursor, custom agent) to the agenttoll.dev MCP endpoint:
https://agenttoll.dev/mcp
Or call the HTTP endpoint directly with an x402-capable fetch client.
Pricing & payment
FAQ
How much does cve_search cost?
$0.02 per call in USDC on Base. No subscriptions or minimums.
Do I need an API key?
No. Payment is handled by the x402 protocol. Your agent wallet sends USDC on Base, the server verifies the transfer, and returns the data.
Which AI models work with cve_search?
Any model that supports MCP — Claude, GPT-4, Gemini, or local models via an MCP client. The tool returns structured JSON that any model can parse.
How do I verify my payment?
After settlement, check /receipt/<tx> for on-chain verification via Basescan. Every payment is a real USDC transfer to 0x62a0D3d9…
