Refines a prompt using local semantic memory, a local AI model for rewriting, and real-time external documentation (Context7) to make it more contextual and efficient.
AI agents call refine_prompt to retrieve information from OpenCode MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs prompt enhancement through information retrieval and local processing. It reads from semantic memory and documentation sources to generate an improved prompt as output. No data is persisted back to external systems, no code is executed, and no irreversible changes occur. The blast radius of misuse is limited to potentially confusing prompt output, which constitutes a low-severity read operation.
From the tool's definition The tool 'refines a prompt using local semantic memory' and external documentation. Key verbs indicate retrieval and processing: 'refines', 'using', 'rewriting' - all read-only operations.
Documented attack patterns abuse exactly the kind of access refine_prompt 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 refine_prompt:
{
"version": "1",
"default": "deny",
"tools": {
"refine_prompt": {}
}
}refine_prompt is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Refines a prompt using local semantic memory, a local AI model for rewriting, and real-time external documentation (Context7) to make it more contextual and efficient. It is categorised as a Read tool in the OpenCode MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenCode MCP Server MCP server in PolicyLayer and add a rule for refine_prompt: 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.
refine_prompt 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 refine_prompt 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 refine_prompt. 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.
refine_prompt is provided by the OpenCode MCP Server MCP server (marlondivino/open-code-as-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.
5 OpenCode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.