AI agents call preview_natural_language_intake to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to parse or preview natural language input to interpret task descriptions, operating locally without external calls. This is fundamentally a read/query operation that extracts or previews data. While 'apply' could suggest mutation, in context it likely means applying the parsing logic to understand input rather than persisting changes to task state.
From the tool's definition Tool is described as 'preview or apply deterministic local natural-language task intake without hosted model calls' - the emphasis on 'preview' and 'local' processing, combined with 'natural-language intake' (parsing/understanding input), indicates this…
Attacks that exploit this kind of access
Preview or apply deterministic local natural-language task intake without hosted model calls. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for preview_natural_language_intake: 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.
preview_natural_language_intake is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the preview_natural_language_intake 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 preview_natural_language_intake. 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.
preview_natural_language_intake 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 →