AI agents use fill_missing_values to create or update resources in DataBeak — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DataBeak environment.
The tool modifies existing data by filling missing/null values, which is a reversible write operation. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). The empty description prevents higher confidence, but the name and context of sibling data-transformation tools strongly suggest a Write classification.
From the tool's definition Tool name 'fill_missing_values' indicates modification of data by populating null or absent values. Sibling tools include 'fill_column_nulls' and 'change_column_type', confirming this server performs data transformation.
Attacks that exploit this kind of access
fill_missing_values. It is categorised as a Write tool in the DataBeak MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DataBeak MCP server in PolicyLayer and add a rule for fill_missing_values: 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 DataBeak. Nothing to install.
fill_missing_values 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 fill_missing_values 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 fill_missing_values. 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.
fill_missing_values is provided by the DataBeak MCP server (jonpspri/databeak). 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 →