Add a todo to a plan, the todo is a step to do the plan
AI agents use add_todo_to_plan to create or update resources in MCP MySQL App — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP MySQL App environment.
This tool creates or modifies data (adding a todo item to a plan) in a reversible manner. There is no deletion, financial impact, code execution, or irreversible data loss. The blast radius is minimal since a todo item in a plan can be removed or corrected. It qualifies as a Write operation per the classification rules.
From the tool's definition Tool description states it 'Add[s] a todo to a plan', which is a create/modify operation that adds a new item to an existing plan structure.
Attacks that exploit this kind of access
Add a todo to a plan, the todo is a step to do the plan. It is categorised as a Write tool in the MCP MySQL App MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP MySQL App MCP server in PolicyLayer and add a rule for add_todo_to_plan: 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 MCP MySQL App. Nothing to install.
add_todo_to_plan 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 add_todo_to_plan 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 add_todo_to_plan. 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.
add_todo_to_plan is provided by the MCP MySQL App MCP server (zalab-inc/mcp-mysql-app). 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 →