Loading MCP server directory, please wait...
Non-invasive AI Agent monitoring — audit every API call to Shopify, Meta Ads, and more
npx @getmcp/cli add io.github.fishcoco-code/guardrly-mcpRequires Python 3.10+. Community-contributed server. Review source before installing.
GUARDRLY_API_KEYYour Guardrly API key from app.guardrly.com/settings
HMAC_SECRETYour HMAC secret from app.guardrly.com/settings MCP Configuration panel
Config file: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"io.github.fishcoco-code/guardrly-mcp": {
"command": "uvx",
"args": [
"guardrly"
],
"env": {
"GUARDRLY_API_KEY": "",
"GUARDRLY_API_URL": "https://api.guardrly.com",
"HMAC_SECRET": ""
}
}
}
}Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
Deploy files, sites, and Dockerfile apps to live URLs + private drives for agent memory.
Self-hosted homelab log intelligence over MCP, CLI, and REST with SQLite/FTS.