AI agents use i1n_push to create or update resources in I1n — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your I1n environment.
The tool creates or modifies data in a remote localization service (i1n) by uploading translation files. This is reversible (translations can be updated or reverted), so it falls under Write rather than Destructive.
From the tool's definition Tool description states 'Push local translation files to i1n' — this is a write operation that modifies remote translation data. The mention of 'diff detection' and 'only changed keys are pushed' confirms it transmits and persists changes to a backend system.
Attacks that exploit this kind of access
Push local translation files to i1n (with diff detection, only changed keys are pushed). It is categorised as a Write tool in the I1n MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the I1n MCP server in PolicyLayer and add a rule for i1n_push: 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 I1n. Nothing to install.
i1n_push 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 i1n_push 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 i1n_push. 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.
i1n_push is provided by the I1n MCP server (pakvothe/i1n-cli). 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 →