AI agents call get_dict_items to retrieve information from UOFastMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays dictionary field definitions for a U2 database file. It is a read-only query operation that returns schema metadata without modifying data or executing code. The filtering options (D/V types) are purely for presentation purposes and do not alter the underlying database state. No data is created, modified, deleted, or overwritten.
From the tool's definition Tool description: 'Get DICT items for a file, optionally filtered by type (D for data fields, V for virtual fields). This shows available field definitions.' The action is retrieval of metadata/schema information with no modification or side effects.
Attacks that exploit this kind of access
Get DICT items for a file, optionally filtered by type (D for data fields, V for virtual fields). This shows available field definitions. It is categorised as a Read tool in the UOFastMCP MCP Server, which means it retrieves data without modifying state.
Register the UOFast MCP server in PolicyLayer and add a rule for get_dict_items: 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 UOFastMCP. Nothing to install.
get_dict_items 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_dict_items 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_dict_items. 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_dict_items is provided by the UOFast MCP server (rokipark/uofastmcp). 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 →