AI agents use filter_data to create or update resources in Office Editor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Office Editor environment.
The server is focused on creating and editing documents. 'filter_data' likely applies a data filter to an Excel worksheet (a reversible Write operation), similar to Excel's filter feature. However, the empty description significantly lowers confidence. It could also be a Read operation if it only queries/filters data without modifying it.
From the tool's definition Tool name 'filter_data' on a server for 'creating and editing Word, Excel, and PowerPoint documents'. Description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access filter_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Office Editor, and nothing reaches the server without passing your rules. This is the rule we recommend for filter_data:
{
"version": "1",
"default": "deny",
"tools": {
"filter_data": {
"limits": [
{
"counter": "filter_data_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}filter_data stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
filter_data. It is categorised as a Write tool in the Office Editor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Office Editor MCP server in PolicyLayer and add a rule for filter_data: 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 Office Editor. Nothing to install.
filter_data 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 filter_data 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 filter_data. 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.
filter_data is provided by the Office Editor MCP server (thewdy/office-editor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 Office Editor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 Office Editor tools catalogued and risk-classified — across an index of 42,500+ MCP servers.