Deep health report — mcp knowledge MCP Resource

Deep health report is one of 19 resources on the mcp knowledge MCP server. Connect the server and your client can attach it as context.

by client

How to attach Deep health report from your client

• Claude Code mcp knowledge Resource/Deep health report run in your project directory
• Claude Desktop mcp knowledge Resource/Deep health report ~/Library/Application Support/Claude/claude_desktop_config.json
• Cursor mcp knowledge Resource/Deep health report ~/.cursor/mcp.json
• VS Code mcp knowledge Resource/Deep health report .vscode/mcp.json
• Zed mcp knowledge Resource/Deep health report ~/.config/zed/settings.json
• Windsurf mcp knowledge Resource/Deep health report ~/.codeium/windsurf/mcp_config.json
• Cline mcp knowledge Resource/Deep health report ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• Gemini CLI mcp knowledge Resource/Deep health report ~/.gemini/settings.json
• Grok mcp knowledge Resource/Deep health report .mcp.json (in your project root)
• ChatGPT mcp knowledge Resource/Deep health report Settings → Connectors → Advanced → Developer mode
• Claude.ai mcp knowledge Resource/Deep health report Settings → Connectors → Add custom connector
• LangChain mcp knowledge Resource/Deep health report pip install langchain-mcp-adapters

Other resources on this server

• Tools catalog with pricing
• x402 pricing tiers
• OFAC SDN latest snapshot
• Combined sanctions metadata
• Last 24h metrics
• Per-tool metrics
• External connectors health
• Gapup-hub circuit breaker state
• Cache statistics
• Tool aliases map
• Recent health alerts
• Job progress events
• Tool deprecation notices
• Active A/B price experiments
• Platform uptime report
• Intent routing map
• Agent cohort analysis — last 90 days
• Performance regression report — last 7 days vs prior week

mcp knowledge also offers 8 prompts — things you invoke, where a resource is context you attach.

Read from the server itself, by connecting to it and calling resources/list on 24 September 2026. A listing does not declare its resources, so asking is the only way to know them, and this is what the server actually offers rather than what its listing claims. Names only are stored; connect the server for each resource's type and contents.