Vulnify is answering right now. Last checked 12 min ago. 981 installs a week from npm. Last commit 15 Oct 2026.
Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.
Today is the operative word: we check Vulnify every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.
claude mcp add mcp --transport http https://mcp.vulnify.io/mcp
{
"mcpServers": {
"mcp": {
"url": "https://mcp.vulnify.io/mcp"
}
}
}
[mcp_servers.mcp]
url = "https://mcp.vulnify.io/mcp"
{
"mcpServers": {
"mcp": {
"url": "https://mcp.vulnify.io/mcp"
}
}
}
{
"mcpServers": {
"mcp": {
"url": "https://mcp.vulnify.io/mcp"
}
}
}
This one needs environment variables set before it will start:
VULNIFY_API_KEY (Vulnify API key (vln_live_... or vln_test_...) for the local stdio process. The hosted server signs in with Vulnify and does not need this variable.), VULNIFY_BASE_URL (API base URL. Defaults to https://api.vulnify.io.).
The author declared them in the registry entry; get the values from the project itself.
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.vulnify.io/mcp | streamable-http | sign-in | 373 ms | 12 min ago |
Tanilo checks the premise before an AI agent acts.
Tently, the AI PR reviewer for GitHub: agents check team decisions before they write code.
Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
Decision-assurance for AI agents: an auditable action boundary + receipt before it acts.
Ask probe402's public record about an x402 or MPP endpoint before an agent pays it.
The body an agent asks before it acts: decide, approve, and keep a signed record on your machine.
Commit policy as code for AI agents: check commit messages, branch names and authors before a push
Human review for AI agents: ask through ActionBox and retrieve a typed decision before proceeding.
Answers built from our own checks of this server.