AI agents call x_search_tweets to retrieve information from X without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Searching tweets retrieves data with no side effects or modifications. Even in an AI agent context, a search operation returns information without creating, modifying, or deleting content. The blast radius of misuse is minimal—an agent might conduct excessive searches or retrieve sensitive information, but cannot cause irreversible harm or financial impact.
From the tool's definition Tool name is 'x_search_tweets' which indicates querying/searching tweets without modifying them. Server description explicitly lists 'searching' as one of the read-only capabilities alongside posting and liking.
Attacks that exploit this kind of access
x_search_tweets. It is categorised as a Read tool in the X MCP Server, which means it retrieves data without modifying state.
Register the X MCP server in PolicyLayer and add a rule for x_search_tweets: 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. Nothing to install.
x_search_tweets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the x_search_tweets 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 x_search_tweets. 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.
x_search_tweets is provided by the X MCP server (mindmadelab/x-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 →