get_sandbox_context
Report whether the CURRENT workspace is itself a sandbox (is_sandbox, status, and the production workspace it belongs to). Call this before risky or experimental changes: if is_sandbox=true you are already in a safe copy; if false, consider creating or switching to a sandbox first.
This record as markdown: /tools/sankahq-sanka-mcp/get-sandbox-context.md
What get_sandbox_context does on Sanka MCP Server
AI agents call get_sandbox_context to retrieve information from Sanka MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_sandbox_context is rated Low
This is a simple informational query that returns the current workspace's sandbox state. It has no side effects, cannot modify data, and serves as a safety check before risky operations. The classification is Read with low severity because it only retrieves metadata about the workspace environment.
From the tool's definition Tool retrieves workspace sandbox status information (is_sandbox, status, production workspace reference) with no ability to modify, delete, or execute operations. Described as providing report/query functionality before changes, not executing changes itself.
Attacks that exploit this kind of access
The rule that runs get_sandbox_context safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sanka MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_sandbox_context, this is the rule to start with:
get_sandbox_context is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Sanka MCP Server, apply this rule, and every get_sandbox_context call is checked against it from then on.
Questions about get_sandbox_context
Report whether the CURRENT workspace is itself a sandbox (is_sandbox, status, and the production workspace it belongs to). Call this before risky or experimental changes: if is_sandbox=true you are already in a safe copy; if false, consider creating or switching to a sandbox first. It is categorised as a Read tool in the Sanka MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sanka MCP Server MCP server in PolicyLayer and add a rule for get_sandbox_context: 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 Sanka MCP Server. Nothing to install.
get_sandbox_context 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_sandbox_context 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_sandbox_context. 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_sandbox_context is provided by the Sanka MCP Server MCP server (sankahq/sanka-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sanka MCP Server, and thousands of servers like it.
This server
Across the catalogue