Continue an existing OpenCode session.
AI agents invoke opencode_continue_session to trigger actions in OpenCode MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of previously-defined or ongoing operations within an OpenCode session. While it doesn't directly execute new commands (that appears to be execute_opencode_command's role), continuing a session resumes external operations whose effects depend on what the session contains.
From the tool's definition Tool allows continuation of an existing OpenCode session which executes terminal-based coding tasks via the OpenCode CLI.
Documented attack patterns abuse exactly the kind of access opencode_continue_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenCode MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for opencode_continue_session:
{
"version": "1",
"default": "deny",
"tools": {
"opencode_continue_session": {
"limits": [
{
"counter": "opencode_continue_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}opencode_continue_session stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Continue an existing OpenCode session. It is categorised as a Execute tool in the OpenCode MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenCode MCP Server MCP server in PolicyLayer and add a rule for opencode_continue_session: 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 MCP Server. Nothing to install.
opencode_continue_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the opencode_continue_session 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 opencode_continue_session. 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.
opencode_continue_session is provided by the OpenCode MCP Server MCP server (nosolosoft/opencode-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenCode MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 OpenCode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.