AI agents use create_inbox_item to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool creates new inbox items and associated tasks, which is a reversible write operation. While it modifies system state by adding data, it does not delete, execute arbitrary code, move funds, or perform irreversible actions. The medium severity reflects that creating spurious tasks could clutter the system and potentially mislead an AI agent's workflow, but the impact is limited and reversible through deletion.
From the tool's definition Tool description states it 'Capture[s] a local inbox item' and 'Creates a linked task by default,' indicating it creates and modifies data in the task management system.
Attacks that exploit this kind of access
Capture a local inbox item from pasted errors, CI logs, git context, files, or GitHub issue URLs. Creates a linked task by default. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for create_inbox_item: 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 Todos. Nothing to install.
create_inbox_item 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 create_inbox_item 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 create_inbox_item. 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.
create_inbox_item is provided by the Todos MCP server (@hasna/todos). 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 →