AI agents use import_issues 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.
The tool creates new tasks/issues in the todo system from external sources and may update existing records during deduplication. This is a Write operation (data creation and modification) rather than Read (it modifies state), Execute (no arbitrary code execution), or Destructive (no irreversible deletion).
From the tool's definition Tool description states it "Import[s]" issues from export files, creating new task records. The dedupe functionality indicates it modifies existing data by preventing duplicates. This is a create/modify operation without irreversible deletion.
Attacks that exploit this kind of access
Import GitHub, Linear, or Jira issues from local JSON export files with dedupe. 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 import_issues: 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.
import_issues 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 import_issues 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 import_issues. 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.
import_issues 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 →