workspace_update · Anythingllm MCP: Risk & Policy

WHAT IT DOES

What workspace_update does on Anythingllm

AI agents use workspace_update 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.

WHY IT NEEDS A POLICY

Why workspace_update needs a policy

This tool creates or modifies data in a reversible manner (Write category). Severity is medium because workspace updates could affect multiple users and configuration, but the blast radius is bounded to workspace scope rather than system-wide or financial impacts.

From the tool's definition Tool name 'workspace_update' and description 'Update workspace' indicate modification of workspace configuration or data. The verb 'update' confirms reversible change operations rather than destructive deletion or financial transactions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

workspace_update Rate-limited

workspace_update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "workspace_update": {
      "limits": [
        {
          "counter": "workspace_update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Anythingllm, so you can run agents against it safely.

FAQ

Questions about workspace_update

What does the workspace_update tool do? +

Update 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.

How do I enforce a policy on workspace_update? +

Register the Anythingllm MCP server in PolicyLayer and add a rule for workspace_update: 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.

What risk level is workspace_update? +

workspace_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit workspace_update? +

Yes. Add a rate_limit block to the workspace_update 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.

How do I block workspace_update completely? +

Set action: deny in the PolicyLayer policy for workspace_update. 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.

What MCP server provides workspace_update? +

workspace_update 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.