mcp-opencode
This server lets you send prompts to opencode models and discover available models/providers.
Send a prompt to an opencode model, optionally specifying a model in
provider/modelformat (defaults togithub-copilot/gpt-4.1).List available models: omit
providerto see all providers with model counts, or pass a provider name to list its models.
Provides access to GitHub Copilot models via a local opencode server, allowing AI agents to query Copilot for code generation, completion, and explanation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-opencode Explain the difference between var, let, and const in JavaScript"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for opencode — query github-copilot models via a persistent opencode server.
Website · Documentation
Features
Zero API key — routes prompts through a locally running opencode server, so no provider credentials are needed in your AI client.
Multi-model support — any model configured in opencode is available; query GPT-4.1, Claude, Gemini, or any other supported provider.
Model filtering — restrict or block models via
MCP_OPENCODE_MODEL_ALLOWandMCP_OPENCODE_MODEL_BLOCKenvironment variables using glob-style patterns.Talk to a live session —
list_sessions,sendandreadlet your assistant hold a conversation with a running opencode session, such as the one open in your TUI, and the exchange shows up there live.Headless jobs —
start_instance,task,wait,list_instancesandstop_instancerun work on a private opencode server per job, with guard rails (no git push, no credentials, no permission prompts) and a ready-madeopencode --servercommand to watch it live.Auto-start — if opencode's background service is not running,
queryandlist_modelsstart it the same way the TUI does.Session isolation — each
querycall creates and destroys its own opencode session, so one-off questions leave nothing behind.Works everywhere — compatible with Claude Desktop, Claude Code, Cursor, Windsurf, VSCode, and any MCP-capable client.
Related MCP server: Remote OpenCode MCP Server
Install
npm install -g @kud/mcp-opencodeRequires opencode 2.x (npm i -g @opencode/cli) with at least one provider configured, and Node.js ≥ 20. For opencode 1.x, stay on @kud/mcp-opencode@1.
Usage
Add the server to your MCP client configuration:
{
"mcpServers": {
"opencode": {
"command": "npx",
"args": ["-y", "@kud/mcp-opencode"]
}
}
}To restrict which models are available, pass environment variables:
{
"mcpServers": {
"opencode": {
"command": "npx",
"args": ["-y", "@kud/mcp-opencode"],
"env": {
"MCP_OPENCODE_MODEL_ALLOW": "github-copilot/*",
"MCP_OPENCODE_MODEL_BLOCK": "github-copilot/gpt-4o-mini"
}
}
}
}Talking to a live opencode session
opencode 2 runs one background service that every TUI window shares, and records where it listens (and its password) in its state directory. The MCP reads that registration, so any window you open with a plain opencode is reachable: no ports, no wrapper.
1. Open opencode and say something. opencode only creates a session once you send the first message.
2. Ask your assistant to talk to it. For example: "list my opencode sessions and ask the one in my-project what it thinks of this plan". It calls list_sessions to find the session, send to talk to it, and read to catch up on its history. Messages appear live in the window, and you can reply there yourself.
A window started with opencode --standalone runs a private server with a throwaway password, so the MCP cannot reach it. To use a server of your own instead of the background service, set MCP_OPENCODE_URL (and MCP_OPENCODE_PASSWORD if it has one); a TUI joins that server with opencode --server <url>.
Running headless jobs
For work you want done in the background rather than in a window you are watching, ask your assistant to start an instance and hand it a task. For example: "start an opencode instance in ~/Projects/my-app, have it add a health-check endpoint, and tell me what changed". It calls:
start_instance({ directory })→{ port, url }: a privateopencode serveon a free port behind a generated password, separate from the background service your windows use.task({ port, prompt })→{ session_id, port, attach }: returns at once while the job runs.wait({ port, session_id })→ status, the last assistant text and the files changed. Call it again if it comes backbusy.stop_instance({ port })when done. Idle instances are reaped afterMCP_OPENCODE_INSTANCE_TTL, and the MCP stops its own instances when it exits.
Guard rails. Nobody is there to answer a permission prompt, so a task's session never gets one: reading, editing and shell commands are allowed, while git push, git remote, gh, npm publish, git reset --hard, web fetches and searches, questions and anything outside the directory are denied. Every deny is set twice: as an opencode permission rule (session and server config) and as a policy, which opencode applies after all rules, so a repository's own opencode config cannot allow it back. The server itself runs with no git credentials (GIT_TERMINAL_PROMPT=0, GIT_SSH_COMMAND=false, an empty credential.helper), without GH_TOKEN/GITHUB_TOKEN, and with its model pinned to MCP_OPENCODE_MODEL.
Sandboxing (opt-in OS sandbox). Set MCP_OPENCODE_SANDBOX=srt to wrap each instance's opencode serve in srt (npm i -g @anthropic-ai/sandbox-runtime), enforced by the OS (macOS sandbox-exec, Linux bubblewrap) rather than by opencode's own permissions. Off by default; when the variable is unset everything behaves exactly as before. Any other non-empty value is refused with an error listing the supported values, and if srt is not on PATH the instance fails to start rather than running unsandboxed.
The server generates an srt settings file per instance (kept in a temp dir under the state dir, removed on stop_instance) and passes it as srt --settings <file> opencode serve … — always explicit, so a stray ~/.srt-settings.json can never decide the policy. The generated file allows writes only to the instance directory (realpath), its git dir(s) (both --git-common-dir and --git-dir, so worktrees work), opencode's own data/config/cache/state dirs (XDG-aware, so provider auth keeps working) and the temp dir; denies reads of credential paths (~/.ssh, ~/.aws, ~/.config/gh, ~/.gnupg, ~/.netrc, ~/.npmrc, **/.env, **/.env.*, ~/Library/Keychains, ~/.config/gcloud, ~/.kube, ~/.docker/config.json, and the background service's service.json files, which hold its password); and allows only these network destinations plus local binding for the server's own port: opencode.ai, *.opencode.ai, models.dev, api.githubcopilot.com, openrouter.ai, github.com, *.github.com, api.github.com, registry.npmjs.org, localhost, 127.0.0.1.
Sandboxed instances also get extra shell denies merged into their opencode permission config (session ruleset and OPENCODE_CONFIG_CONTENT alike): rm -rf*, sudo *, curl *|* and wget *|*. These are deny, never ask — a headless session cannot answer and would hang — and they are heuristic glob matches, a second layer behind the OS sandbox, not a guarantee. The opencode.ai / *.opencode.ai / api.githubcopilot.com entries were verified against the opencode 2.1.2 binary's strings (Zen API, model registry at models.opencode.ai, Copilot provider), and openrouter.ai serves the openrouter/* models; models.dev, the 1.x registry, is kept for older lookups; the rest are assumed useful for public clones and npm installs. Non-existent allowWrite entries are dropped when the file is written, so a missing opencode dir cannot break the wrap on any platform.
This is defence in depth, not a guarantee: it raises the cost of escape and of credential or network misuse, but a determined agent inside the sandbox still has the instance directory, git, and whatever the allowlist permits. Combine it with the guard rails above and review what jobs do.
Model fallback. A job tries [its model, ...MCP_OPENCODE_MODEL_FALLBACK] once each, in order. When the session stays in retry for MCP_OPENCODE_RETRY_TIMEOUT_SECONDS (default 90) or its run ends in a provider error (a provider.* error type, or model not found), the watchdog interrupts it, switches the session's model and re-prompts the same session on the next model, so history and worktree edits carry over. When the list is exhausted the job settles as error. wait and list_instances report the current model and the fallbacks taken ({ from, to, reason, at }), and wait reports retry as its own status.
Watching or stepping in. Paste the attach command from task into a terminal. It opens the session in the TUI against the instance, with the instance's password:
OPENCODE_PASSWORD=… opencode --server http://127.0.0.1:53817 --session ses_…Instance registry
Instances are recorded in ~/.local/state/mcp-opencode/instances.json (or $MCP_OPENCODE_STATE_DIR/instances.json). Other tools may read it directly; this shape is a stable contract:
[
{
"runtime": "opencode", // always "opencode" for now
"sandbox": "srt", // "srt" when OS-sandboxed, else null
"port": 53817, // where the server listens, on 127.0.0.1
"pid": 41234, // the opencode serve process (or the srt wrapper, when sandboxed)
"mcpPid": 41200, // the mcp-opencode process that started it
"directory": "/Users/me/Projects/my-app",
"startedAt": "2026-10-02T12:04:34.453Z",
"password": "…", // basic-auth password (user "opencode") for the server
// one entry per task, appended when task starts it
"sessions": [
{
"id": "ses_…",
"title": "add health check",
"model": "github-copilot/gpt-4.1",
"startedAt": "2026-10-02T12:04:35.021Z",
// model switches so far, oldest first; empty until one happens
"fallbacks": [
{
"from": "github-copilot/gpt-4.1",
"to": "github-copilot/gpt-5",
"reason": "retry timeout after 90s (attempt 3: rate limited)",
"at": "2026-10-02T12:06:05.111Z",
},
],
},
],
},
]Live state (busy or idle, last activity) is deliberately not in the file: read it from the server at http://127.0.0.1:<port> with the row's password. The file is written owner-only (0600) because it holds those passwords; list_instances leaves them out. A sandboxed row also carries an internal sandboxSettingsDir with the generated srt settings file; it is cleaned up on stop and is not part of the contract.
Environment variables
Variable | Default | Purpose |
| the background service | Use this opencode server for everything instead of the background service and its discovery |
| none | Password for |
|
| Seconds |
|
| Model |
| all | Comma-separated models or |
| none | Comma-separated models or patterns to block. Filters apply to |
| none | Ordered, comma-separated fallback models ( |
|
| Seconds a job's session may stay continuously in |
|
| Seconds every session on an instance may sit idle before the reaper stops it |
|
| Where the instance registry ( |
| unset (off) |
|
| generated | Path to an srt settings file used as |
Available tools
Tool | Description |
| Send a prompt to an opencode model. Accepts |
| List models available through the running opencode server. Accepts an optional |
| List sessions on the background service and on headless instances, most recent first, with the port(s) each is served on. Accepts an optional |
| Send a message to an existing session and return the reply. Accepts |
| Read a session's recent messages as a condensed transcript. Accepts |
| Start a private headless opencode server in |
| Start a job on an instance: |
| Wait for a job ( |
| Reap, then list registered instances with their task sessions' live status, current |
| Interrupt busy sessions, stop the server on |
Development
git clone https://github.com/kud/mcp-opencode.git
cd mcp-opencode
npm install
npm run build
npm testUse the local .mcp.json to connect Claude Code to your dev build, or npm run inspect to open the MCP Inspector against the compiled output.
Script | Purpose |
| Run from source via |
| Compile TypeScript to |
| Run the Vitest test suite |
| Open MCP Inspector against the built server |
📚 Full documentation → mcp-opencode/docs
Available Tools
2 toolslist_modelsA
List models available for use. Without a provider, returns providers with model counts. Pass a provider name to list its models. Respects allow/block filters (allow: all).
Inputs: provider.
queryA
Send a prompt to an opencode model. Defaults to github-copilot/gpt-4.1. Filters — allow: all. Use list_models to see what's available.
Inputs: prompt (required), model.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools are clearly distinct: 'query' sends a prompt to a model, while 'list_models' retrieves available models. No ambiguity or overlap in their purposes.
Both tool names use a consistent verb or verb_noun pattern ('query', 'list_models'). The naming is clear and predictable.
With only 2 tools, the server feels minimal but not unreasonable for a simple query-and-list interface. However, the scope seems narrow for a full model interaction server.
The server covers basic querying and model listing, but lacks tools for configuration (e.g., setting filters or providers) or advanced features like streaming or model metadata details. Notable gaps exist.
Maintenance
Related MCP Connectors
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
An MCP server that gives your AI access to the source code and docs of all public github repos
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server to check GitHub Copilot quota, rate-limit status, and reset times from any MCP client.132 npmMIT
- AlicenseNot gradedqualityCmaintenanceA Model Context Protocol (MCP) server that enables remote access to OpenCode AI coding agent, allowing MCP-compatible clients to leverage OpenCode's capabilities.MIT
- AlicenseAqualityCmaintenanceMCP server for GitHub Copilot that allows querying any Copilot model programmatically using existing Copilot CLI credentials, with support for file attachments and model discovery.226 npmMIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that lets an AI coding agent delegate implementation work to the OpenCode CLI, choosing an explicit provider + model on every call.3MIT