AI agents invoke process_directory to trigger actions in MinerU MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Given the server context (MinerU document processing with automatic splitting/merging of large files), 'process_directory' most likely triggers batch document processing operations on a directory of files, which constitutes executing an external operation. The empty description lowers confidence significantly.
From the tool's definition Tool name 'process_directory' on a document processing MCP server; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access process_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MinerU MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for process_directory:
{
"version": "1",
"default": "deny",
"tools": {
"process_directory": {
"limits": [
{
"counter": "process_directory_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}process_directory stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
process_directory. It is categorised as a Execute tool in the MinerU MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MinerU MCP Server MCP server in PolicyLayer and add a rule for process_directory: 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 MinerU MCP Server. Nothing to install.
process_directory is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the process_directory 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_directory. 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_directory is provided by the MinerU MCP Server MCP server (neosun100/mineru-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MinerU MCP 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 MinerU MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.