AI agents call whoami to retrieve information from Eyeot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves authentication context and permission metadata. It has no side effects, does not create, modify, or delete data, and does not trigger external operations. It is a standard identity/authentication query, making it Read category. Severity is low because misuse would only expose user/org information to the calling agent, not grant unauthorized actions or cause blast damage.
From the tool's definition Tool name 'whoami' and description 'Retrieve the authenticated user + active organisation + permissions' indicate a query operation that retrieves user identity and metadata without modifying or executing actions.
Attacks that exploit this kind of access
Récupérer l'utilisateur authentifié + organisation active + permissions. À APPELER AVANT toute réponse mentionnant l'org/user/plan/role. It is categorised as a Read tool in the Eyeot MCP Server, which means it retrieves data without modifying state.
Register the Eyeot MCP server in PolicyLayer and add a rule for whoami: 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 Eyeot. Nothing to install.
whoami 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 whoami 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 whoami. 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.
whoami is provided by the Eyeot MCP server (https://erp.eyeot.fr/api/v1/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 →