AI agents call search-communities 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.
This tool searches and retrieves community information based on keyword input. It does not create, modify, delete, or execute any state-changing operations. The action is purely informational retrieval, consistent with other read-only tools on the server (get-home-timeline, get-user-details, get-tweets). Misuse would be limited to discovering communities; the blast radius is minimal.
From the tool's definition Tool name 'search-communities' and description 'Search for X communities by keyword' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
Search for X communities by keyword. 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 search-communities: 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.
search-communities 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-communities 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-communities. 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-communities is provided by the X MCP server (siddheshutd/x-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search-communities is one line of X's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →