AI agents call get_dataset 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 dataset metadata from a public open data portal with no write, execute, destructive, or financial capabilities. The empty description and naming pattern alongside other 'get_' and 'list_' tools (which are clearly read-only) indicate this is a retrieval operation with no side effects.
From the tool's definition Tool name 'get_dataset' and sibling tools (get_group, get_organization, get_resource, list_datasets, list_organizations) all follow retrieval patterns consistent with CKAN API read operations on the Moroccan Open Data portal.
Attacks that exploit this kind of access
get_dataset. 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_dataset: 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_dataset 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_dataset 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_dataset. 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_dataset 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 →