Verify API token
AI agents call auth_verify to retrieve information from Anythingllm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Verification of an API token is a read-only operation that authenticates and validates credentials without side effects. It retrieves or queries the validity state of a token. This poses minimal risk as it does not create, modify, delete, or execute operations. Severity is low because misuse would only allow an agent to check token validity, not gain unauthorized access or trigger harmful actions.
From the tool's definition Tool name and description indicate it 'Verify API token' — a query/check operation that determines if a token is valid. No data is modified, deleted, or executed.
Attacks that exploit this kind of access
Verify API token. It is categorised as a Read tool in the Anythingllm MCP Server, which means it retrieves data without modifying state.
Register the Anythingllm MCP server in PolicyLayer and add a rule for auth_verify: 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 Anythingllm. Nothing to install.
auth_verify 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 auth_verify 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 auth_verify. 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.
auth_verify is provided by the Anythingllm MCP server (moliver28/anythingllm-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 →