AI agents call get_organization to retrieve information from Datagovma without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves organizational information from the Moroccan Open Data portal. No write, delete, execute, or financial operations are performed. The empty description reduces confidence slightly, but the naming pattern and sibling tools strongly indicate a simple query/retrieval operation typical of CKAN's read-only informational endpoints.
From the tool's definition Tool name 'get_organization' and context of sibling tools (get_dataset, get_resource, get_group, list_*) which are all read-only retrieval operations against a CKAN API for an open data portal.
Attacks that exploit this kind of access
get_organization. It is categorised as a Read tool in the Datagovma MCP Server, which means it retrieves data without modifying state.
Register the Datagovma MCP server in PolicyLayer and add a rule for get_organization: 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 Datagovma. Nothing to install.
get_organization 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_organization 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_organization. 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_organization is provided by the Datagovma MCP server (mohtamimad/datagovma-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 →