Generate API key
AI agents use system_generate_api_key to create or update resources in Anythingllm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Anythingllm environment.
Generating an API key is a Write operation: it creates a new, reversible secret credential in the system. Severity is high because a misused API key generation could create unauthorized access credentials for the AnythingLLM platform, enabling an agent to provision keys for malicious use.
From the tool's definition Tool name contains 'generate' which creates a new artifact (API key). Description states 'Generate API key' — a create operation that produces a new credential.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Generate API key. It is categorised as a Write tool in the Anythingllm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Anythingllm MCP server in PolicyLayer and add a rule for system_generate_api_key: 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_generate_api_key is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the system_generate_api_key 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_generate_api_key. 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_generate_api_key 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 →