transkribus_recog_train_la_citlab
Start CITlab Layout Analysis model training for a collection.
This record as markdown: /tools/io-github-lazyants-transkribus/transkribus-recog-train-la-citlab.md
What transkribus_recog_train_la_citlab does on Transkribus
AI agents invoke transkribus_recog_train_la_citlab to trigger actions in Transkribus. 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.
Why transkribus_recog_train_la_citlab is rated High
This tool initiates a computationally intensive, long-running training job on an external ML system (CITlab). While not immediately destructive or financial, it represents an Execute action because it triggers a complex external process with significant side effects (resource allocation, model generation, time/cost expenditure).
From the tool's definition 'Start CITlab Layout Analysis model training' indicates triggering an external machine learning training operation whose execution and resource consumption depend on collection selection and training parameters.
Attacks that exploit this kind of access
The rule that runs transkribus_recog_train_la_citlab 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_train_la_citlab, this is the rule to start with:
transkribus_recog_train_la_citlab 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Transkribus, apply this rule, and every transkribus_recog_train_la_citlab call is checked against it from then on.
Questions about transkribus_recog_train_la_citlab
Start CITlab Layout Analysis model training for a collection. It is categorised as a Execute tool in the Transkribus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Transkribus MCP server in PolicyLayer and add a rule for transkribus_recog_train_la_citlab: 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_train_la_citlab 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 transkribus_recog_train_la_citlab 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_train_la_citlab. 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_train_la_citlab 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