Update a tool
AI agents use farmbot_update_tool to create or update resources in Farmbot Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Farmbot Agent environment.
This tool modifies tool configuration in the FarmBot system. The update operation is reversible—a subsequent update can undo the changes—which classifies it as Write rather than Destructive. Severity is medium because misconfiguration of tools could affect automated gardening tasks, but the impact is limited to tool parameters and is correctable.
From the tool's definition Tool name 'farmbot_update_tool' and description 'Update a tool' indicate modification of existing data. The sibling tools all use 'add_' prefix for creation, while this tool uses 'update_' which is characteristic of reversible data modification.
Attacks that exploit this kind of access
Update a tool. It is categorised as a Write tool in the Farmbot Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Farmbot Agent MCP server in PolicyLayer and add a rule for farmbot_update_tool: 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 Farmbot Agent. Nothing to install.
farmbot_update_tool 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 farmbot_update_tool 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 farmbot_update_tool. 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.
farmbot_update_tool is provided by the Farmbot Agent MCP server (kieranklaassen/farmbot-agent-cli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →