Pandas DataFrame
AI agents use create_xlsx_from_dataframe to create or update resources in KnowledgeBaseMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KnowledgeBaseMCP environment.
This tool creates new Excel files or modifies existing workbooks by writing DataFrame data. It is a Write operation because file creation/modification is reversible (files can be deleted or overwritten). It does not delete data (not Destructive), does not execute arbitrary code (not Execute), and does not involve financial transactions.
From the tool's definition Tool name 'create_xlsx_from_dataframe' and sibling context showing 'create_xlsx_report', 'create_xlsx_workbook', 'append_to_xlsx' indicate the tool creates or modifies Excel files.
Attacks that exploit this kind of access
Pandas DataFrame. It is categorised as a Write tool in the KnowledgeBaseMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KnowledgeBase MCP server in PolicyLayer and add a rule for create_xlsx_from_dataframe: 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 KnowledgeBaseMCP. Nothing to install.
create_xlsx_from_dataframe 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 create_xlsx_from_dataframe 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 create_xlsx_from_dataframe. 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.
create_xlsx_from_dataframe is provided by the KnowledgeBase MCP server (mehmetozcan-zz/knowledgebasemcp). 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 →