Get any contact by UID.
AI agents call myob_contact_get to retrieve information from MYOB Codex MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact data by unique identifier. Retrieval operations that do not modify, delete, or execute code are classified as Read. The server description confirms read-only tools are provided by default. The severity is low because retrieving contact information poses minimal risk even if misused by an agent — it exposes data but does not alter, delete, or commit financial transactions.
From the tool's definition Tool name is 'myob_contact_get' and description states 'Get any contact by UID' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get any contact by UID. It is categorised as a Read tool in the MYOB Codex MCP MCP Server, which means it retrieves data without modifying state.
Register the MYOB Codex MCP server in PolicyLayer and add a rule for myob_contact_get: 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_contact_get is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the myob_contact_get 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_contact_get. 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_contact_get 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 →