AI agents use save_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 persisting document changes to storage, which is a Write operation rather than Read (no querying), Execute (no arbitrary code execution), Destructive (changes are reversible by reopening the original or using undo), or Financial.
From the tool's definition Tool name 'save_document' and description '保存当前文档' (save current document) indicate the tool persists modifications to a Word document file.
Documented attack patterns abuse exactly the kind of access save_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 save_document:
{
"version": "1",
"default": "deny",
"tools": {
"save_document": {
"limits": [
{
"counter": "save_document_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_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.
保存当前文档. 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 save_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.
save_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 save_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 save_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.
save_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.