AI agents call social_search_users to retrieve information from Logiqical without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user information based on search criteria. It is a read-only operation that queries data without creating, modifying, deleting, or executing any side effects. The severity is low because searching for public user information poses minimal risk even if misused by an AI agent.
From the tool's definition Tool is named 'social_search_users' with description 'Search Arena users by name or handle' — it performs a search/query operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Search Arena users by name or handle. It is categorised as a Read tool in the Logiqical MCP Server, which means it retrieves data without modifying state.
Register the Logiqical MCP server in PolicyLayer and add a rule for social_search_users: 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 Logiqical. Nothing to install.
social_search_users 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 social_search_users 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 social_search_users. 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.
social_search_users is provided by the Logiqical MCP server (logiqical-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 →