transkribus_job_undo

Undo the results of a completed job.

SERVERTranskribus SOURCE@lazyants/transkribus-mcp-server

Critical RISK CLASS

Category Destructive

Parameters 00 required

Recommended Hiddensee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-lazyants-transkribus/transkribus-job-undo.md

WHAT IT DOES

What transkribus_job_undo does on Transkribus

AI agents call transkribus_job_undo to permanently remove resources in Transkribus, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

RISK

Why transkribus_job_undo is rated Critical

Undoing job results reverses previously completed work (e.g., HTR/OCR transcription results applied to documents), which is likely irreversible or at least destructive to the output data produced by that job. This goes beyond a simple write/update as it removes or reverts processed results that may not be recoverable.

From the tool's definition "Undo the results of a completed job"

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs transkribus_job_undo safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Transkribus, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For transkribus_job_undo, this is the rule to start with:

transkribus_job_undo Hidden

transkribus_job_undo is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "transkribus_job_undo"
  ]
}

RESTRICT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Transkribus, apply this rule, and every transkribus_job_undo call is checked against it from then on.

FAQ

Questions about transkribus_job_undo

What does the transkribus_job_undo tool do? +

Undo the results of a completed job. It is categorised as a Destructive tool in the Transkribus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on transkribus_job_undo? +

Register the Transkribus MCP server in PolicyLayer and add a rule for transkribus_job_undo: 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 Transkribus. Nothing to install.

What risk level is transkribus_job_undo? +

transkribus_job_undo is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit transkribus_job_undo? +

Yes. Add a rate_limit block to the transkribus_job_undo 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 transkribus_job_undo completely? +

Set action: deny in the PolicyLayer policy for transkribus_job_undo. 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 transkribus_job_undo? +

transkribus_job_undo is provided by the Transkribus MCP server (@lazyants/transkribus-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Transkribus, and thousands of servers like it.

This server

All 301 Transkribus tools → Critical-risk tools on this server →

Across the catalogue

delete_cron_job on cPanel MCP Server → All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Blast radius →Tool call approval →