transkribus_recog_update
Update a recognition model in a collection.
This record as markdown: /tools/io-github-lazyants-transkribus/transkribus-recog-update.md
What transkribus_recog_update does on Transkribus
AI agents use transkribus_recog_update to create or update resources in Transkribus, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Transkribus environment.
Why transkribus_recog_update is rated Medium
This tool modifies an existing recognition model configuration or metadata within a collection. While the change is reversible (the model can be updated again or reverted), updating a recognition model could affect OCR/HTR processing results across documents using that model, creating potential downstream impact on dependent workflows.
From the tool's definition Tool name contains 'update' and description states 'Update a recognition model in a collection.' Update operations modify existing data reversibly.
Attacks that exploit this kind of access
The rule that runs transkribus_recog_update 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_update, this is the rule to start with:
transkribus_recog_update 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Transkribus, apply this rule, and every transkribus_recog_update call is checked against it from then on.
Questions about transkribus_recog_update
Update a recognition model in a collection. It is categorised as a Write tool in the Transkribus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Transkribus MCP server in PolicyLayer and add a rule for transkribus_recog_update: 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_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the transkribus_recog_update 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_update. 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_update 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.
This server
Across the catalogue