Search for tweets using a query
AI agents call search_tweets to retrieve information from X MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and retrieves tweet data based on search criteria, which is a classic Read operation with no side effects. The blast radius is minimal: an attacker could enumerate tweets or extract public information, but cannot modify state, execute code, or cause financial harm. Severity is low because the impact is limited to information disclosure of already-public data.
From the tool's definition 'Search for tweets using a query' — this is a read-only operation that retrieves data from X without modifying, creating, or deleting any content.
Attacks that exploit this kind of access
Search for tweets using a query. It is categorised as a Read tool in the X MCP Server MCP Server, which means it retrieves data without modifying state.
Register the X MCP Server MCP server in PolicyLayer and add a rule for 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 MCP Server. Nothing to install.
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 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 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.
search_tweets is provided by the X MCP Server MCP server (krishna-paulraj/x-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 →