Get users a user is following
AI agents call get_following to retrieve information from Agent Twitter Client without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward query operation that retrieves a list of users that a specified user follows. It performs no modifications, deletions, executions, or financial operations. While it accesses social graph data that could be considered sensitive in aggregate, the blast radius of misuse is limited to information disclosure rather than account compromise, unauthorized actions, or financial harm.
From the tool's definition Tool name 'get_following' and description 'Get users a user is following' indicate a retrieval operation with no side effects or modifications to data.
Attacks that exploit this kind of access
Get users a user is following. It is categorised as a Read tool in the Agent Twitter Client MCP Server, which means it retrieves data without modifying state.
Register the Agent Twitter Client MCP server in PolicyLayer and add a rule for get_following: 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 Agent Twitter Client. Nothing to install.
get_following 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 get_following 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 get_following. 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.
get_following is provided by the Agent Twitter Client MCP server (theo-nash/twitter-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 →