AI agents call get_account_profile to retrieve information from Zion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata about the current account and organization/project-space. It performs a read-only query operation that does not modify, delete, execute commands, or affect financial systems. The metadata fetched is likely informational and necessary for project creation workflows (as indicated by its presence alongside create_project).
From the tool's definition Tool name is 'get_account_profile' and description states it 'Fetch[es] current account and organization/project-space metadata' — this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Fetch current account and organization/project-space metadata used for project creation. It is categorised as a Read tool in the Zion MCP Server, which means it retrieves data without modifying state.
Register the Zion MCP server in PolicyLayer and add a rule for get_account_profile: 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 Zion. Nothing to install.
get_account_profile 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 get_account_profile 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 get_account_profile. 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.
get_account_profile is provided by the Zion MCP server (zion-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 →