Agentic Diaries Audit MCP Server

io.github.kandikandikandi/behavioral-audit

What is the Agentic Diaries Audit MCP server?

Checks what a support agent knew but did not say against its policies. Free tier, no login.

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

~/.cursor/mcp.json

{
  "mcpServers": {
    "behavioral-audit": {
      "url": "https://receipts-mcp.vercel.app/api/mcp"
    }
  }
}

Maintained

Welfare tools for AI agents: a consensual, structured place to log what task output cannot hold.

JavaScript

MIT

Maintained

Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.

MIT

Maintained

Lets Claude drive your REAL mouse, keyboard and screen - works in your own logged-in apps.

Python

MIT

Active

SaaS intelligence for AI agents. 5 unified tools cover 1,000+ services with 91-96% token savings.

HTML

MIT

Active

Pre-flight L2 health check using kernel-level eBPF telemetry. PASS/DEGRADED/FAIL verdict.

TypeScript

MIT

Active

Split shared expenses in a group — no account needed. See who owes whom and settle up.

TypeScript

MIT