AI agents invoke i18n_publish_profile to trigger actions in Shipeasy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes external operations: rebuilding a KV manifest and purging CDN caches. These are not simple writes — they actively modify distributed infrastructure state and invalidate cached content globally. A CDN purge is a significant operational action with wide blast radius (can disrupt live users if done incorrectly), placing this firmly in Execute.
From the tool's definition "rebuild KV manifest + purge CDN" — triggers external operations (CDN purge and KV manifest rebuild) that affect production infrastructure
Attacks that exploit this kind of access
Publish a chunk or whole profile: rebuild KV manifest + purge CDN. It is categorised as a Execute tool in the Shipeasy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Shipeasy MCP server in PolicyLayer and add a rule for i18n_publish_profile: 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 Shipeasy. Nothing to install.
i18n_publish_profile is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the i18n_publish_profile 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 i18n_publish_profile. 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.
i18n_publish_profile is provided by the Shipeasy MCP server (shipeasy-ai/mcp). 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 →