opencode_config_get
Read the OpenCode config (~/.config/opencode/opencode.json or env-overridden path). Returns the resolved path, default agent, top-level model + small_model, plus the per-agent build/plan models, all configured providers (with baseURL — useful for OpenRouter, remote Tailscale Ollama, or other BYOK...
This record as markdown: /tools/io-github-kivanccakmak-yaver/opencode-config-get.md
What opencode_config_get does on Yaver
AI agents call opencode_config_get to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
device_id | string | — | Optional remote device ID |
Parameters from the server's own tool schema.
Why opencode_config_get is rated Low
This tool retrieves configuration settings without side effects. The device_id parameter allows reading another machine's config but remains a read-only operation. The returned data (paths, model identifiers, provider baseURLs) is informational only. No actual execution, creation, modification, or destruction of data occurs.
From the tool's definition Tool explicitly performs only 'Read the OpenCode config' with description emphasizing retrieval: 'Returns the resolved path, default agent, top-level model + small_model, plus the per-agent build/plan models, all configured providers'.
Attacks that exploit this kind of access
The rule that runs opencode_config_get safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For opencode_config_get, this is the rule to start with:
opencode_config_get 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 Yaver, apply this rule, and every opencode_config_get call is checked against it from then on.
Questions about opencode_config_get
Read the OpenCode config (~/.config/opencode/opencode.json or env-overridden path). Returns the resolved path, default agent, top-level model + small_model, plus the per-agent build/plan models, all configured providers (with baseURL — useful for OpenRouter, remote Tailscale Ollama, or other BYOK OpenAI-compatible backends), and a flat list of model identifiers. Optional device_id reads another owned Yaver machine's config. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
opencode_config_get accepts 1 parameter: device_id. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for opencode_config_get: 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 Yaver. Nothing to install.
opencode_config_get 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 opencode_config_get 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_config_get. 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_config_get is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue