AI agents use set_workspace_trust to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool modifies security-relevant configuration (workspace trust/permissions) but does so reversibly. It's a Write operation rather than Execute because it doesn't run arbitrary code or trigger external operations—it configures access control. The 'medium' severity reflects that misconfiguration could grant unintended permissions, affecting multiple tasks or users in the workspace, but changes can be reverted.
From the tool's definition Tool name is 'set_workspace_trust' and description states it will 'Create or update a local workspace trust and permission profile.' The verbs 'create' and 'update' indicate reversible data modification.
Attacks that exploit this kind of access
Create or update a local workspace trust and permission profile. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for set_workspace_trust: 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 Todos. Nothing to install.
set_workspace_trust 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 set_workspace_trust 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 set_workspace_trust. 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.
set_workspace_trust is provided by the Todos MCP server (@hasna/todos). 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 →