AI agents use convert_batch to create or update resources in MCP Docling Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Docling Server environment.
The tool converts documents to markdown or other formats (per server description), which creates new data outputs. This is a Write operation—it produces new data artifacts through document conversion. Severity is medium because batch processing multiple documents could consume resources or create large outputs, but the operation is reversible (converted outputs can be deleted).
From the tool's definition Tool named 'convert_batch' with description 'Convert multiple documents in batch mode' indicates document conversion/processing that creates output artifacts (converted documents).
Documented attack patterns abuse exactly the kind of access convert_batch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Docling Server, and nothing reaches the server without passing your rules. This is the rule we recommend for convert_batch:
{
"version": "1",
"default": "deny",
"tools": {
"convert_batch": {
"limits": [
{
"counter": "convert_batch_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}convert_batch 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.
Convert multiple documents in batch mode. It is categorised as a Write tool in the MCP Docling Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Docling Server MCP server in PolicyLayer and add a rule for convert_batch: 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 MCP Docling Server. Nothing to install.
convert_batch 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 convert_batch 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 convert_batch. 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.
convert_batch is provided by the MCP Docling Server MCP server (zanetworker/mcp-docling). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Docling Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 MCP Docling Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.