batch_save · MD Webcrawl MCP: Risk & Policy

WHAT IT DOES

What batch_save does on MD Webcrawl MCP

AI agents use batch_save to create or update resources in MD Webcrawl MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MD Webcrawl MCP environment.

WHY IT NEEDS A POLICY

Why batch_save needs a policy

The tool creates or modifies files by saving crawled content in batch, which is a reversible write operation. Severity is medium because bulk file creation could consume storage or overwrite existing files, but effects are generally reversible.

From the tool's definition Tool name 'batch_save' combined with server purpose of 'extract and save content as markdown files' indicates the tool saves/writes data. Description is empty, limiting precision.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

batch_save Rate-limited

batch_save 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "batch_save": {
      "limits": [
        {
          "counter": "batch_save_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MD Webcrawl MCP, so you can run agents against it safely.

FAQ

Questions about batch_save

What does the batch_save tool do? +

batch_save. It is categorised as a Write tool in the MD Webcrawl MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on batch_save? +

Register the MD Webcrawl MCP server in PolicyLayer and add a rule for batch_save: 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 MD Webcrawl MCP. Nothing to install.

What risk level is batch_save? +

batch_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit batch_save? +

Yes. Add a rate_limit block to the batch_save 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.

How do I block batch_save completely? +

Set action: deny in the PolicyLayer policy for batch_save. 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.

What MCP server provides batch_save? +

batch_save is provided by the MD Webcrawl MCP server (jmh108/md-webcrawl-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.