AI agents use create_post to create or update resources in Posterly — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Posterly environment.
This tool creates new social media content that is published to external platforms. While the description confusingly includes 'DESTRUCTIVE WRITE', the actual operation is Write (creates/modifies content reversibly). It should be categorized as Write rather than Destructive, since social media posts can be edited or deleted after publication.
From the tool's definition Tool description states "Schedule or immediately publish a social media post" and explicitly labels it as "DESTRUCTIVE WRITE".
Attacks that exploit this kind of access
Schedule or immediately publish a social media post. This is a DESTRUCTIVE WRITE that creates content on the user\. It is categorised as a Write tool in the Posterly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Posterly MCP server in PolicyLayer and add a rule for create_post: 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 Posterly. Nothing to install.
create_post 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_post 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_post. 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_post is provided by the Posterly MCP server (posterly-mcp-server). 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 →