Split long text into a numbered X (Twitter) thread (1/x).
AI agents use format_thread to create or update resources in Growth Hacker MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Growth Hacker MCP environment.
This tool generates or modifies text content (formatting long text into a Twitter thread structure) but does not execute external actions, delete data, or trigger irreversible changes. It is a reversible text transformation tool used for content creation. The output is text that a user would then choose to post, not an automated posting action.
From the tool's definition Tool name 'format_thread' and description 'Split long text into a numbered X (Twitter) thread' indicates the tool creates formatted text output for social media posting.
Attacks that exploit this kind of access
Split long text into a numbered X (Twitter) thread (1/x). It is categorised as a Write tool in the Growth Hacker MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Growth Hacker MCP server in PolicyLayer and add a rule for format_thread: 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 Growth Hacker MCP. Nothing to install.
format_thread 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 format_thread 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 format_thread. 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.
format_thread is provided by the Growth Hacker MCP server (samusilv/growth-hacker-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 →