Get user
AI agents call get_all_workspaces to retrieve information from Retable MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves workspace information without creating, modifying, or deleting data. The action is purely informational with no side effects. Severity is low because workspaces are typically metadata containers; exposure of this tool poses minimal risk compared to destructive or financial operations on the same server.
From the tool's definition Tool name 'get_all_workspaces' and description 'Get user' indicate data retrieval with no modification. Sibling tools confirm pattern: 'get_project' and similar query operations are clearly Read actions.
Attacks that exploit this kind of access
Get user. It is categorised as a Read tool in the Retable MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Retable MCP Server MCP server in PolicyLayer and add a rule for get_all_workspaces: 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 Retable MCP Server. Nothing to install.
get_all_workspaces is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_all_workspaces 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 get_all_workspaces. 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.
get_all_workspaces is provided by the Retable MCP Server MCP server (retable-io/mcp-server). 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 →