AI agents use write_dict_item to create or update resources in UOFastMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UOFastMCP environment.
This tool creates or modifies dictionary metadata in a U2 database, which affects how data is structured and interpreted across the system. While reversible (unlike Destructive), it can have wide-ranging side effects if misused—modifying field definitions could break queries, reports, or application logic.
From the tool's definition Tool name 'write_dict_item' and description 'Write or update a DICT item in a file' explicitly indicate data modification operations. DICT items are schema/metadata objects in U2 databases that define file structures and field mappings.
Attacks that exploit this kind of access
Write or update a DICT item in a file. It is categorised as a Write tool in the UOFastMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the UOFast MCP server in PolicyLayer and add a rule for write_dict_item: 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.
write_dict_item is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the write_dict_item 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 write_dict_item. 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.
write_dict_item 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 →