Search Twitter/X for tweets by keyword.
AI agents call twitter_search to retrieve information from Twitter/X MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries public tweets matching specified keywords. It is a read-only operation that does not create, modify, delete, or execute any code or financial transactions. The blast radius of misuse is minimal—an agent could retrieve large amounts of public data or perform aggressive searches, but no permanent changes or harmful actions are possible through this tool alone.
From the tool's definition Tool name 'twitter_search' and description 'Search Twitter/X for tweets by keyword' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Search Twitter/X for tweets by keyword. It is categorised as a Read tool in the Twitter/X MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Twitter/X MCP Server MCP server in PolicyLayer and add a rule for twitter_search: 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 Twitter/X MCP Server. Nothing to install.
twitter_search 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 twitter_search 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 twitter_search. 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.
twitter_search is provided by the Twitter/X MCP Server MCP server (miles0sage/twitter-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 →