AI agents invoke opencode_run 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 executes terminal-based coding operations via the OpenCode AI agent based on user prompts. The effects are dependent on the prompt content and could range from harmless reads to destructive system modifications.
From the tool's definition Tool name 'opencode_run' combined with description 'Run OpenCode with a simple prompt message' indicates execution of an AI coding agent that processes arbitrary prompts.
Documented attack patterns abuse exactly the kind of access opencode_run 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_run:
{
"version": "1",
"default": "deny",
"tools": {
"opencode_run": {
"limits": [
{
"counter": "opencode_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}opencode_run 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.
Run OpenCode with a simple prompt message. 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_run: 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_run 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_run 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_run. 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_run 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.