AI agents use process_local_document to create or update resources in Docx_MCP_cj — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docx_MCP_cj environment.
This tool modifies state by uploading local documents to cloud storage, which is a reversible Write operation. It does not execute arbitrary code, delete data permanently, or move money.
From the tool's definition Tool description states it 'processes local .docx files and uploads to cloud' (处理本地.docx文件并上传到云端). The upload to cloud endpoint represents data creation/modification in a remote system.
Documented attack patterns abuse exactly the kind of access process_local_document gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Docx_MCP_cj, and nothing reaches the server without passing your rules. This is the rule we recommend for process_local_document:
{
"version": "1",
"default": "deny",
"tools": {
"process_local_document": {
"limits": [
{
"counter": "process_local_document_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}process_local_document 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.
【本地文档处理工具】处理本地.docx文件并上传到云端. It is categorised as a Write tool in the Docx_MCP_cj MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docx_MCP_cj MCP server in PolicyLayer and add a rule for process_local_document: 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 Docx_MCP_cj. Nothing to install.
process_local_document 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 process_local_document 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 process_local_document. 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.
process_local_document is provided by the Docx_MCP_cj MCP server (rockcj/docx_mcp_cj). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 54 Docx_MCP_cj tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
54 Docx_MCP_cj tools catalogued and risk-classified — across an index of 42,500+ MCP servers.