[CUSTOM] Calls the Marketo REST API directly (not Adobe's native MCP).
AI agents call custom_describe_custom_object to retrieve information from Marketo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name contains 'describe', which conventionally means fetching schema or metadata about a custom object, a read-only operation. However, the description only says it 'Calls the Marketo REST API directly' without specifying what the call does, which lowers confidence.
From the tool's definition 'custom_describe_custom_object' — 'describe' strongly implies a metadata/schema retrieval operation (no side effects)
Attacks that exploit this kind of access
[CUSTOM] Calls the Marketo REST API directly (not Adobe's native MCP). It is categorised as a Read tool in the Marketo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Marketo MCP Server MCP server in PolicyLayer and add a rule for custom_describe_custom_object: 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 Marketo MCP Server. Nothing to install.
custom_describe_custom_object 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 custom_describe_custom_object 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 custom_describe_custom_object. 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.
custom_describe_custom_object is provided by the Marketo MCP Server MCP server (tyron-pretorius/marketo-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 →