OpenCode MCP server
Commit 12. Nov. 2026Delegiert rechenintensive Aufgaben von Orchestrator-Modellen an isolierte OpenCode-Subagents, um die Qualität des Context Windows zu bewahren und Token-Kosten zu senken.
Auch bekannt als alejandro-technology/opencode-mcp, mcp-server-opencode
- Stars
- 6
- Tools
- 10
- Downloads, 30 Tage
- —
- Neueste Version
- —
- Letzter Commit
- 12. Nov. 2026
- Lizenz
- —
Was ist OpenCode MCP?
OpenCode ist ein MCP server. Delegiert rechenintensive Aufgaben von Orchestrator-Modellen an isolierte OpenCode-Subagents, um die Qualität des Context Windows zu bewahren und Token-Kosten zu senken. Er stellt 10 Tools bereit, etwa opencode_start_server, opencode_stop_server, opencode_list_agents.
Zusammenfassung generiert aus dem README des Projekts
Über OpenCode MCP server
Das Delegieren rechenintensiver Aufgaben von einem Orchestrator an isolierte Subagents ist das Kernfeature von opencode-mcp für Entwickler, die Claude Code, Codex, Cursor, Antigravity oder Pi nutzen. Indem du das Lesen großer Dateien, umfangreiche Suchen und repetitive Test-Loops an OpenCode-Subagents im Hintergrund auslagerst, verhinderst du Context Window Bloat und senkst die Token-Kosten. Dieser Ansatz bewahrt die Reasoning-Qualität deines primären Lead Agents, indem sein Context schlank bleibt und sich auf die Orchestrierung konzentriert.
Nutzer müssen Node.js 18+ und OpenCode 1.x auf ihrem Systempfad installiert und konfiguriert haben, um diesen Server zu nutzen. Der Server verwaltet asynchrone Aufgaben über spezifische Tools wie opencode_start_task und opencode_wait_for_task, was die parallele Ausführung mehrerer Untersuchungen ermöglicht. Er unterstützt das Ausführen von Aufgaben in einem gemeinsamen Verzeichnis oder innerhalb isolierter, verwalteter Git Worktrees, um Code-Änderungen organisiert zu halten. Das System bietet detaillierte Usage-Reports, einschließlich Metriken nach Provider und Model aufgeschlüsselt, um die Kosten der delegierten Sessions im Blick zu behalten.
Was du damit machen kannst
- 1Parallele Task-AusführungStarte mehrere Investigations- oder Implementierungsaufgaben parallel, ohne den Orchestrator zu blockieren.
- 2Erhalt des Context WindowsVermeide es, den Context deines primären Agents durch das Lesen großer Dateien oder umfangreiche Suchergebnisse zu überladen.
- 3Iteratives Subagent-DebuggingSende Follow-up-Prompts an eine bestehende Task-Session, um iterative Arbeitsschritte mit einem Subagent durchzuführen.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du OpenCode MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenOpenCode MCP in Claude Code installieren
$ claude mcp add opencode-mcp -- npx -y mcp-server-opencodeOpenCode MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"opencode-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}OpenCode MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"opencode-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}OpenCode MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"opencode-mcp","type":"stdio","command":"npx","args":["-y","mcp-server-opencode"]}'OpenCode MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"opencode-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}OpenCode MCP in Codex installieren
$ codex mcp add opencode-mcp -- npx -y mcp-server-opencodeOpenCode MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.opencode-mcp] command = "npx" args = ["-y", "mcp-server-opencode"]
OpenCode MCP in Gemini CLI installieren
$ gemini mcp add -s user opencode-mcp npx -- -y mcp-server-opencodeOpenCode MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"opencode-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}OpenCode MCP tools 10
Erkannt aus dem READMEopencode_start_serveropencode_stop_serveropencode_list_agentsopencode_start_taskopencode_continue_taskopencode_cancel_taskopencode_cleanup_workspaceopencode_get_task_statusopencode_get_task_resultopencode_wait_for_task
| opencode_start_server | — | |
| opencode_stop_server | — | |
| opencode_list_agents | — | |
| opencode_start_task | — | |
| opencode_continue_task | — | |
| opencode_cancel_task | — | |
| opencode_cleanup_workspace | — | |
| opencode_get_task_status | — | |
| opencode_get_task_result | — | |
| opencode_wait_for_task | — |
Konfiguration
MCP_TOOL_TIMEOUTOPENCODE_MCP_SMOKE_MODEL
| Name | Beschreibung | Typ |
|---|---|---|
| MCP_TOOL_TIMEOUT | — | |
| OPENCODE_MCP_SMOKE_MODEL | — |
Automatisierte Checks
Geluften am 13. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbaralejandro-technology/opencode-mcp is public and reachablegithub.com/alejandro-technology/opencode-mcp ↗Bestanden
- Paket nennt dieses Repository als Quellemcp-server-opencode names alejandro-technology/opencode-mcp as sourcenpmjs.com/package/mcp-server-opencode ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)No build attestation published for this releaseNicht geprüft
- Open Source Lizenz (OSI)No licenseBefund
- Commit oder Release im letzten JahrLast commit or release 2026-11-12github.com/alejandro-technology/opencode-mcp ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from mcp-server-opencodeBestanden
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell10 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenopencode-mcp
Keep your lead agent lean and save tokens by delegating heavy tasks to background subagents.
opencode-mcp is a Model Context Protocol (MCP) server that connects orchestrator hosts (Claude Code, Codex, Cursor, Antigravity, Pi) with OpenCode subagents. Instead of polluting your orchestrator's context window with large file reads, extensive search outputs, and repetitive test runs, you delegate those tasks to isolated subagents and receive only concise, structured results.
Why this matters (Context Window Economics)
- 🧠 Prevent Context Rot & Bloat: Monolithic agents suffer reasoning degradation as the context fills up. Keeping your lead agent as an orchestrator preserves high reasoning quality.
- 💰 Slash Token Costs: Running large exploratory reads or test-fix loops directly inside your primary (Fable/Opus, Astra/Sol) session repeatedly bills for thousands of cached tokens on every follow-up turn. Subagents run in isolated sessions using optimal models.
- ⚡ Asynchronous Parallel Execution: Dispatch multiple investigation or implementation tasks in parallel without blocking the orchestrator.
Quick install
Requires Node.js 18+ and OpenCode 1.x installed and configured (opencode must be on your PATH, with at least one provider/model set up) — this server spawns and drives OpenCode instances.
For Claude Code:
claude mcp add opencode -- npx -y mcp-server-opencode
For Codex:
codex mcp add opencode -- npx -y mcp-server-opencode
See Installation for manual config, and from-source options.
Tools
| Tool | Description |
|---|---|
opencode_start_server |
Start a new OpenCode server instance in the MCP process working directory |
opencode_stop_server |
Stop a running OpenCode server instance |
opencode_list_agents |
List agents/models available on a server instance (optional directory selects a project) |
opencode_start_task |
Delegate a task to an agent by starting a new session and prompt (optional agent / model override) |
opencode_continue_task |
Send a follow-up prompt to an existing task's session for iterative back-and-forth with the subagent |
opencode_cancel_task |
Abort a running delegated task by cancelling its session |
opencode_cleanup_workspace |
Explicitly remove an owned Git worktree after task reports finalize; dirty worktrees require opt-in discard |
opencode_get_task_status |
Poll the status of a delegated task (pending / running / completed / failed / empty / cancelled); optional include_progress adds a partial output snippet and the currently running tool while it's still running |
opencode_get_task_result |
Fetch the final result of a completed task |
opencode_wait_for_task |
Long-poll one or more delegated tasks until they finish (mode: "all" or "any") or the timeout elapses; optional include_progress best-effort enriches unfinished tasks within the same deadline, falling back to the last observed status/progress when time runs out |
Delegation workflow and model-selection guidance are provided through the MCP server instructions.
How it works
Task delegation is asynchronous: opencode_start_task returns a task_id and run_id without waiting, so hosts can start tasks in parallel. Tasks use the selected directory by default; managed Git worktrees are optional. Poll for status and retrieve results separately. If dispatch is uncertain, use the returned IDs to check or cancel the task instead of retrying it.
Execution reports and caller checks
Start and continuation calls can include expected_changes and checks. Status and result responses report workspace changes, verification, diagnostics, and evidence; pass a run_id to retrieve a historical run. Workspace changes are best-effort evidence, since concurrent writers can make attribution uncertain.
Shared directories and managed worktrees
Tasks run in the selected existing directory (shared, the default), or in an isolated managed Git worktree based on a commit. Worktrees are kept after execution; use opencode_cleanup_workspace with its workspace_id after reports are finalized. Cleanup only removes worktrees managed by this server, and dirty worktrees require explicit discard.
Usage reporting
Status, wait, and result responses include run and session usage snapshots, with metrics broken down by provider and model. Missing metrics remain unknown rather than zero, and cost is OpenCode-reported—not an invoice total. Finalized runs retain their snapshots for historical retrieval.
Task history and workspace ownership are held in memory for the lifetime of the MCP process. Restarting loses these records; retained worktrees are not automatically rediscovered.
Installation
Prerequisites
- Node.js 18+
- OpenCode 1.x installed and configured (
opencodemust be on yourPATH, with at least one provider/model set up) — this server spawns and drives OpenCode instances.
The current adapter uses the OpenCode v1 SDK/API and was validated against OpenCode 1.18.34 , 1.19.5. OpenCode 2.x is not yet supported.
Option 1 — npm (recommended)
The package is published as mcp-server-opencode. No cloning or building needed — point your MCP host at npx:
For Claude Code, one command does it:
claude mcp add opencode -- npx -y mcp-server-opencode
Or manually
{
"mcpServers": {
"opencode": {
"command": "npx",
"args": ["-y", "mcp-server-opencode"]
}
}
}
For Codex, add the server to ~/.codex/config.toml:
[mcp_servers.opencode]
command = "npx"
args = ["-y", "mcp-server-opencode"]
Or install it globally and use the binary directly:
npm install -g mcp-server-opencode
{
"mcpServers": {
"opencode": {
"command": "opencode-mcp"
}
}
}
Option 2 — from source
git clone https://github.com/alejandro-technology/opencode-mcp.git
cd opencode-mcp
pnpm install
pnpm build
Then point your MCP host at the built entrypoint:
{
"mcpServers": {
"opencode": {
"command": "node",
"args": ["/path/to/opencode-mcp/build/src/index.js"]
}
}
}
Restart your MCP host after editing the config; the opencode_* tools should appear in its tool list.
Configuration
MCP_TOOL_TIMEOUT
opencode_wait_for_task accepts a timeout_ms input, but it's clamped to a server-side maximum so a single call stays inside the calling host's own MCP request timeout. That maximum defaults to 55000 ms and is configurable via MCP_TOOL_TIMEOUT.
The default is deliberately low: MCP hosts abort long tool requests with MCP error -32001: Request timed out before the tool can answer (observed on OpenCode hosts and the MCP Inspector at 100s+), so a graceful timed_out: true payload at 55s always beats a dead transport. Loop the wait — call opencode_wait_for_task again while timed_out is true — instead of raising timeout_ms. Raise this only when your host demonstrably tolerates longer tool requests.
MCP_TOOL_TIMEOUT can be set two ways:
-
Environment variable — set it in the MCP server config:
{ "mcpServers": { "opencode": { "command": "node", "args": ["/path/to/opencode-mcp/build/src/index.js"], "env": { "MCP_TOOL_TIMEOUT": "1200000" } } } } -
CLI argument — pass
MCP_TOOL_TIMEOUT=<ms>as an extra arg to the server process:{ "mcpServers": { "opencode": { "command": "node", "args": [ "/path/to/opencode-mcp/build/src/index.js", "MCP_TOOL_TIMEOUT=1200000" ] } } }
If both are present, the environment variable takes precedence over the CLI argument. Invalid or non-numeric values fall back to the 55000 ms default.
Permissions and trust
Headless tasks automatically answer permission prompts. Set OPENCODE_MCP_EXTERNAL_DIR to read-only (default), allow, or deny to control external-directory requests. An environment variable takes precedence over an OPENCODE_MCP_EXTERNAL_DIR=<policy> CLI argument; explicit OpenCode deny rules remain in effect.
Use this server only with trusted hosts and repositories. Git worktrees isolate source changes, not OS permissions: agents and caller-provided checks run as your local user, not in a security sandbox.
Development
Project structure
src/
├── index.ts # MCP server entrypoint (stdio transport, shutdown handlers)
└── modules/
├── tools/ # One file per MCP tool, registered in index.ts
└── shared/ # Cross-tool infrastructure (selected modules below)
├── server-registry.ts # Tracks running OpenCode servers
├── task-registry.ts # Task/session identity and per-run history
├── opencode-client.ts # SDK clients, status derivation, and progress
├── run-observer.ts # Background run finalization and result caching
├── execution-report.ts # Workspace evidence and executable checks
├── execution-usage.ts # Run/session usage aggregation
├── workspace-manager.ts # Managed Git worktree lifecycle
├── permissions.ts # Headless permission decisions and responses
├── instructions.ts # Delegation workflow and model-selection guidance
├── config.ts # MCP_TOOL_TIMEOUT resolution
└── mcp-result.ts # JSON tool result helpers
Each module ships with a *.test.ts Vitest suite under the parallel tests/ tree mirroring src/.
Getting started
Use Node.js 22.18+ for development and smoke tests (native TypeScript execution); CI checks Node.js 22 and 24. The published server retains its Node.js 18+ runtime requirement.
pnpm install
pnpm dev # runs the server through the MCP Inspector (tsx, no build needed)
Other scripts:
pnpm test # vitest run
pnpm test:coverage # vitest run --coverage
pnpm lint # biome check
pnpm lint:write # biome check --write
pnpm build # clean tsc build to ./build (also the source typecheck)
Real OpenCode smoke tests
The opt-in smoke harness starts a real OpenCode server and removes its temporary fixtures afterward. It is not part of default CI.
pnpm smoke --message-id-only # non-billable message-ID contract probe
pnpm smoke # full smoke; requires credentials and may incur model charges
The full smoke covers reports, usage, continuation, cancellation, isolated worktrees, and cleanup. Its default model is openai/gpt-6-luna; override it with an exact enabled model ID:
OPENCODE_MCP_SMOKE_MODEL=provider/model pnpm smoke
OpenCode MCP Fragen
Wie füge ich OpenCode MCP zu Claude Code hinzu?
Führe claude mcp add opencode-mcp -- npx -y mcp-server-opencode in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich OpenCode MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet OpenCode MCP?
Er stellt 10 Tools bereit, darunter opencode_start_server, opencode_stop_server, opencode_list_agents, opencode_start_task, opencode_continue_task.
Wie hilft dieser Server beim Context Window Management?
Er verhindert Context Rot und Bloat, indem er das Lesen großer Dateien, umfangreiche Suchen und repetitive Testläufe an isolierte Subagents delegiert, die dem Lead Agent nur prägnante Ergebnisse zurückgeben.
Kann ich mehrere Aufgaben gleichzeitig ausführen?
Ja, die Aufgaben-Delegation erfolgt asynchron. So kannst du mehrere Investigations- oder Implementierungsaufgaben parallel starten, ohne den Orchestrator zu blockieren.
Was sind die Systemvoraussetzungen für die Installation?
Du benötigst Node.js 18+ sowie eine installierte und im PATH konfigurierte OpenCode 1.x Version.