collab_workspace_open
Legacy-compatible workspace open. New independent processes should use collab_session_start.
This record as markdown: /tools/dev-agenttool-agenttool/collab-workspace-open.md
What collab_workspace_open does on Agenttool
AI agents use collab_workspace_open to create or update resources in Agenttool, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agenttool environment.
Why collab_workspace_open is rated Medium
An AI agent can call collab_workspace_open faster than any human can review: one bad instruction and it creates or modifies resources in Agenttool by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs collab_workspace_open safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agenttool, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For collab_workspace_open, this is the rule to start with:
collab_workspace_open 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Agenttool, apply this rule, and every collab_workspace_open call is checked against it from then on.
Questions about collab_workspace_open
Legacy-compatible workspace open. New independent processes should use collab_session_start. It is categorised as a Write tool in the Agenttool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agenttool MCP server in PolicyLayer and add a rule for collab_workspace_open: 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 Agenttool. Nothing to install.
collab_workspace_open 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 collab_workspace_open 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 collab_workspace_open. 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.
collab_workspace_open is provided by the Agenttool MCP server (https://api.agenttool.dev/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agenttool, and thousands of servers like it.
This server
Across the catalogue