Create workspace
AI agents use workspace_create 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.
This tool creates a new workspace, which is a reversible operation that adds data to the system. It does not execute arbitrary code, delete data, or move financial resources. The blast radius is limited to workspace scope, though improper use could clutter the system or create unauthorized collaboration spaces.
From the tool's definition Tool name 'workspace_create' and description 'Create workspace' indicate creation of a new data structure within the AnythingLLM platform. The verb 'create' is characteristic of Write operations.
Attacks that exploit this kind of access
Create workspace. 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 workspace_create: 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.
workspace_create 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 workspace_create 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 workspace_create. 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.
workspace_create 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 →