AI agents use update_plan_step to create or update resources in Melo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Melo environment.
This tool creates or modifies plan metadata reversibly. It does not execute scripts, delete data, or trigger financial transactions. While it could have downstream effects if a malformed plan is created, the direct action is data modification (Write category).
From the tool's definition Tool name 'update_plan_step' and description 'Set a step' indicate modification of plan data. In the context of an agentic Roblox Studio server managing development cycles, this writes/modifies plan state rather than executing external operations or deleting…
Attacks that exploit this kind of access
Set a step. It is categorised as a Write tool in the Melo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Melo MCP server in PolicyLayer and add a rule for update_plan_step: 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 Melo. Nothing to install.
update_plan_step 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 update_plan_step 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 update_plan_step. 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.
update_plan_step is provided by the Melo MCP server (yannyhl/linkedsword-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 →