Approve a prepared MYOB write. The approval_phrase must be exactly 'APPROVE <operation_id>'.
AI agents use myob_approval_approve to create or update resources in MYOB Codex MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MYOB Codex MCP environment.
This tool approves previously-prepared write operations on financial data in MYOB. While approval mechanisms add a safety layer, the tool itself executes reversible modifications to accounting records (bills, accounts, bank transactions, etc.).
From the tool's definition Tool description states it 'Approve a prepared MYOB write', and the operation involves approving mutating actions on a financial accounting system (MYOB AccountRight cloud).
Attacks that exploit this kind of access
Approve a prepared MYOB write. The approval_phrase must be exactly 'APPROVE <operation_id>'. It is categorised as a Write tool in the MYOB Codex MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MYOB Codex MCP server in PolicyLayer and add a rule for myob_approval_approve: 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 MYOB Codex MCP. Nothing to install.
myob_approval_approve is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the myob_approval_approve 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.
Set action: deny in the PolicyLayer policy for myob_approval_approve. 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.
myob_approval_approve is provided by the MYOB Codex MCP server (jaeko44/myob-codex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →