AI agents use bookmark_tweet to create or update resources in X (Twitter) MCP server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your X (Twitter) MCP server environment.
This tool creates a reversible bookmark association between a user and a tweet. It modifies user data (bookmarks list) but does not delete, execute code, or involve financial transactions. The action is easily undone (via delete_bookmark), making it a low-severity Write operation.
From the tool's definition "Adds the tweet to bookmarks" — creates a new bookmark entry
Documented attack patterns abuse exactly the kind of access bookmark_tweet gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and X (Twitter) MCP server, and nothing reaches the server without passing your rules. This is the rule we recommend for bookmark_tweet:
{
"version": "1",
"default": "deny",
"tools": {
"bookmark_tweet": {
"limits": [
{
"counter": "bookmark_tweet_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}bookmark_tweet stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Adds the tweet to bookmarks. It is categorised as a Write tool in the X (Twitter) MCP server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the X (Twitter) MCP server MCP server in PolicyLayer and add a rule for bookmark_tweet: 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 X (Twitter) MCP server. Nothing to install.
bookmark_tweet 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 bookmark_tweet 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 bookmark_tweet. 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.
bookmark_tweet is provided by the X (Twitter) MCP server MCP server (rafaljanicki/x-twitter-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 24 X (Twitter) MCP server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
24 X (Twitter) MCP server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.