AI agents call who_am_i to retrieve information from SEED MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data (system identity) with no capability to modify, delete, or execute operations. It is purely informational and read-only. Severity is low because identity information disclosure has minimal blast radius—it does not expose sensitive secrets, modify data, execute code, or trigger external actions. The confidence is high due to the clear read-only nature of identity queries.
From the tool's definition Tool name 'who_am_i' and description 'Return unified system identity' indicate a retrieval operation that queries and returns identity information without side effects.
Attacks that exploit this kind of access
Return unified system identity. It is categorised as a Read tool in the SEED MCP MCP Server, which means it retrieves data without modifying state.
Register the SEED MCP server in PolicyLayer and add a rule for who_am_i: 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 SEED MCP. Nothing to install.
who_am_i 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 who_am_i 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 who_am_i. 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.
who_am_i is provided by the SEED MCP server (sancovp/seed-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 →