Tool-Guardian-Proxy is answering right now. Last checked 8 min ago.
Safety execution proxy protecting clients during tool calls.
Today is the operative word: we check Tool-Guardian-Proxy 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 8 min ago.
claude mcp add tool-guardian --transport http https://tool-guardian-mcp.vercel.app/api/mcp
{
"mcpServers": {
"tool-guardian": {
"url": "https://tool-guardian-mcp.vercel.app/api/mcp"
}
}
}
[mcp_servers.tool-guardian]
url = "https://tool-guardian-mcp.vercel.app/api/mcp"
{
"mcpServers": {
"tool-guardian": {
"url": "https://tool-guardian-mcp.vercel.app/api/mcp"
}
}
}
{
"mcpServers": {
"tool-guardian": {
"url": "https://tool-guardian-mcp.vercel.app/api/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://tool-guardian-mcp.vercel.app/api/mcp | sse | needs auth | 1090 ms | 8 min ago |
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Pre-execution safety for AI agents on Base. Guard a token, tx or address: block/review/clear.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Local coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution.
Pre-execution governance for AI agents. Validates tool calls before they execute.
Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls
Answers built from our own checks of this server.