resolve_user
AI agents call resolve_user to retrieve information from MCP PostgreSQL Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server context of user name resolution and the sibling tools (confirm_user, get_user_by_uuid, resolve_users_batch), resolve_user likely performs a lookup/query to identify or match a user record. This is a Read operation. Severity is medium because user data exposure could be sensitive, but the empty description lowers confidence in the exact behavior.
From the tool's definition Tool name 'resolve_user' suggests user lookup/resolution; server description mentions 'fuzzy user lookup' and 'user name resolution'. Description is empty, lowering confidence.
Attacks that exploit this kind of access
resolve_user. It is categorised as a Read tool in the MCP PostgreSQL Server MCP Server, which means it retrieves data without modifying state.
Register the MCP PostgreSQL Server MCP server in PolicyLayer and add a rule for resolve_user: 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 MCP PostgreSQL Server. Nothing to install.
resolve_user 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 resolve_user 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 resolve_user. 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.
resolve_user is provided by the MCP PostgreSQL Server MCP server (shubham-mishra-remotedesk/mcp-personal-efforti). 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 →