AI agents call osidb_whoami to retrieve information from Osidb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves identity information about the authenticated user. It performs a simple query with no data modification, deletion, code execution, or financial implications. The narrow scope (identity lookup only) and read-only nature justify 'low' severity. High confidence due to clear documentation and consistency with server's read-only design.
From the tool's definition Tool queries current authenticated user profile from /osidb/whoami endpoint. Description explicitly states it retrieves user information with no modification or side effects.
Attacks that exploit this kind of access
Current authenticated OSIDB user / profile (from /osidb/whoami). It is categorised as a Read tool in the Osidb MCP Server, which means it retrieves data without modifying state.
Register the Osidb MCP server in PolicyLayer and add a rule for osidb_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 Osidb. Nothing to install.
osidb_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 osidb_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 osidb_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.
osidb_whoami is provided by the Osidb MCP server (vdanen/osidb-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 →