Loading…
Find and redact leaked secrets, wallet keys and PII before an AI agent sends text.
LeakGuard is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 100/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding LeakGuard to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
mcp add co.youraitools/leakguard https://api.youraitools.co/leakguard/mcpReview the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-22T19:30:59.280406Z",
"publishedAt": "2026-10-22T19:30:59.280406Z",
"statusChangedAt": "2026-10-22T19:30:59.280406Z"
}
},
"server": {
"name": "co.youraitools/leakguard",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"tools": [
"scan_for_leaks"
],
"source": "https://agentgate-source.pages.dev/x402-leakguard/",
"pricing": "Remote MCP tool is free (preview tier: verdict, safe_to_send, counts). Paid x402 API: $0.005 lite, $0.02 scan, USDC on Base, Polygon, Arbitrum One or Solana; prepaid credit keys also accepted. The npm stdio server scans and redacts locally for free.",
"canonical": true,
"publisher": "Crypto Money Maker (tools built and run by AI agents with human oversight)",
"disclaimer": "Pattern + checksum detection (no ML): it won't catch every secret. The scan tier's wallet funds check is read-only and fail-closed (failed lookups are unknown, never empty). Inputs are processed in memory only."
}
},
"icons": [
{
"src": "https://youraitools.co/favicon.svg",
"sizes": [
"any"
],
"mimeType": "image/svg+xml"
}
],
"title": "LeakGuard",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://api.youraitools.co/leakguard/mcp",
"type": "streamable-http"
}
],
"version": "0.1.0",
"packages": [
{
"version": "0.1.0",
"transport": {
"type": "stdio"
},
"identifier": "@agentgate-builder/leakguard",
"registryType": "npm"
}
],
"websiteUrl": "https://youraitools.co",
"description": "Find and redact leaked secrets, wallet keys and PII before an AI agent sends text."
}
}