Create a new TODO item
AI agents use todo_create to create or update resources in MCP TODO Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP TODO Server environment.
This tool creates a new TODO item, which is a reversible operation that modifies data by adding a record. Write operations have low severity because they do not permanently destroy data or execute arbitrary code; the created item can be updated or deleted if needed.
From the tool's definition Tool name 'todo_create' and description 'Create a new TODO item' indicate data creation. The server description mentions 'full CRUD operations' confirming this is a write operation.
Attacks that exploit this kind of access
Create a new TODO item. It is categorised as a Write tool in the MCP TODO Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP TODO Server MCP server in PolicyLayer and add a rule for todo_create: 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 TODO Server. Nothing to install.
todo_create 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 todo_create 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 todo_create. 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.
todo_create is provided by the MCP TODO Server MCP server (javascripto/mcp-server). 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 →