Switch context to a different workspace (for subsequent operations)
AI agents use switch_workspace to create or update resources in Sidvy MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sidvy MCP Server environment.
This tool changes application state (the active workspace context) for subsequent operations. While it does not create, modify, or delete data directly, it alters which workspace will be affected by follow-up operations, making it a Write-category tool.
From the tool's definition "Switch context to a different workspace" indicates a state-changing operation that modifies the active workspace context for subsequent operations, which is a contextual write operation.
Attacks that exploit this kind of access
Switch context to a different workspace (for subsequent operations). It is categorised as a Write tool in the Sidvy MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sidvy MCP Server MCP server in PolicyLayer and add a rule for switch_workspace: 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 Sidvy MCP Server. Nothing to install.
switch_workspace 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 switch_workspace 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 switch_workspace. 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.
switch_workspace is provided by the Sidvy MCP Server MCP server (martinhjartmyr/sidvy-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 →