AI agents call search_user to retrieve information from Boma MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation to locate users by email criteria. It retrieves data without side effects, matching the Read category definition (retrieves or queries data; no side effects). The severity is low because the blast radius of misuse is limited to potential exposure of user identities/email addresses within the Boma platform, which is a relatively contained information disclosure risk.
From the tool's definition Tool name 'search_user' and description 'Search for a user by email or partial email' indicate a query operation that retrieves user information without modifying, deleting, or executing any actions.
Attacks that exploit this kind of access
Search for a user by email or partial email. It is categorised as a Read tool in the Boma MCP MCP Server, which means it retrieves data without modifying state.
Register the Boma MCP server in PolicyLayer and add a rule for search_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 Boma MCP. Nothing to install.
search_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 search_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 search_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.
search_user is provided by the Boma MCP server (nicolasvegam/boma-mcp). 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 →