AI agents call instances to retrieve information from Opencode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple query/listing operation that retrieves and displays status information about remote coding environment instances. It has no capability to modify, delete, or execute operations - it only reads and returns data about what machines are connected and whether they are busy or idle.
From the tool's definition Tool name and description indicate it 'List all connected opencode instances with their current status' - a retrieval operation that provides information about available machines with no modification or side effects.
Attacks that exploit this kind of access
List all connected opencode instances with their current status (busy/idle). Call this to see what machines are available. It is categorised as a Read tool in the Opencode MCP Server, which means it retrieves data without modifying state.
Register the Opencode MCP server in PolicyLayer and add a rule for instances: 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 Opencode. Nothing to install.
instances 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 instances 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 instances. 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.
instances is provided by the Opencode MCP server (klutometis/opencode-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 →