transkribus_recog_delete
Delete a recognition model from a collection.
This record as markdown: /tools/io-github-lazyants-transkribus/transkribus-recog-delete.md
What transkribus_recog_delete does on Transkribus
AI agents call transkribus_recog_delete 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.
Why transkribus_recog_delete is rated Critical
This tool permanently removes a recognition model, which cannot be undone. Deletion of assets is a destructive action with high blast radius if misused by an AI agent, as it destroys a trained model resource that may be expensive or time-consuming to recreate. The action is irreversible and affects stored data.
From the tool's definition Tool name contains 'delete' and description states 'Delete a recognition model from a collection.' — irreversible removal of data.
Attacks that exploit this kind of access
The rule that runs transkribus_recog_delete 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_recog_delete, this is the rule to start with:
transkribus_recog_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Transkribus, apply this rule, and every transkribus_recog_delete call is checked against it from then on.
Questions about transkribus_recog_delete
Delete a recognition model from a collection. 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.
Register the Transkribus MCP server in PolicyLayer and add a rule for transkribus_recog_delete: 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.
transkribus_recog_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the transkribus_recog_delete 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 transkribus_recog_delete. 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.
transkribus_recog_delete 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.
More on Transkribus, and thousands of servers like it.
Across the catalogue