reconcile · Bookie MCP: Risk & Policy

WHAT IT DOES

What reconcile does on Bookie

AI agents invoke reconcile to trigger actions in Bookie. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why reconcile needs a policy

reconcile triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reconcile Rate-limited

reconcile stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "reconcile": {
      "limits": [
        {
          "counter": "reconcile_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Bookie, so you can run agents against it safely.

FAQ

Questions about reconcile

What does the reconcile tool do? +

Match a bank/card statement (CSV) against the ledger to mark postings as cleared. Two-step: run with mode=. It is categorised as a Execute tool in the Bookie MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on reconcile? +

Register the Bookie MCP server in PolicyLayer and add a rule for reconcile: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Bookie. Nothing to install.

What risk level is reconcile? +

reconcile is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit reconcile? +

Yes. Add a rate_limit block to the reconcile rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block reconcile completely? +

Set action: deny in the PolicyLayer policy for reconcile. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides reconcile? +

reconcile is provided by the Bookie MCP server (yuens1002/bookie). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.