Check API token
AI agents call system_check_token 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.
Checking a token is a retrieval and validation operation with no side effects. It queries the state of an API token without modifying it, executing code, or performing destructive actions. The tool merely verifies authentication status or token validity, making it a Read category tool with low severity.
From the tool's definition Tool name 'system_check_token' combined with description 'Check API token' indicates a verification/query operation. The action is to check or validate an existing token, not to create, modify, delete, or execute operations.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Check 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 system_check_token: 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.
system_check_token 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 system_check_token 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 system_check_token. 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.
system_check_token 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 →