AI agents use write_field to create or update resources in Doc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Doc environment.
This tool creates or modifies data reversibly by writing/updating field values in Excel documents. It does not delete data (Destructive) or execute arbitrary code (Execute), but it does change document content. Given the context of a document analysis server processing Excel files, unauthorized writes could alter financial records, data integrity, or critical spreadsheet contents.
From the tool's definition Tool name is 'write_field' and description indicates it writes field values ('写入字段值') to documents, specifically Excel files ('仅Excel支持'). The action is to modify data in Excel spreadsheets.
Attacks that exploit this kind of access
写入字段值(仅Excel支持). It is categorised as a Write tool in the Doc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Doc MCP server in PolicyLayer and add a rule for write_field: 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 Doc. Nothing to install.
write_field 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_field 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_field. 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_field is provided by the Doc MCP server (jiahuidegit/doc-mcp-server). 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 →