OpenCode MCP server
Commit Nov 12, 2026Delegates heavy tasks from orchestrator models to isolated OpenCode subagents to preserve context window quality and reduce token costs.
Also known as alejandro-technology/opencode-mcp, mcp-server-opencode
- Stars
- 6
- Tools
- 10
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 12, 2026
- License
- —
What is OpenCode MCP?
OpenCode delegates heavy tasks from orchestrator models to isolated OpenCode subagents to preserve context window quality and reduce token costs. It exposes 10 tools, such as opencode_start_server, opencode_stop_server, opencode_list_agents.
Summary generated from the project's README
About OpenCode MCP server
Delegating heavy computational tasks from an orchestrator to isolated subagents is what opencode-mcp enables for developers using Claude Code, Codex, Cursor, Antigravity, or Pi. By offloading large file reads, extensive searches, and repetitive test loops to background OpenCode subagents, you prevent context window bloat and reduce token costs. This approach preserves the reasoning quality of your primary lead agent by keeping its context lean and focused on orchestration.
Users must have Node.js 18+ and OpenCode 1.x installed and configured on their system path to use this server. The server manages asynchronous tasks through specific tools like opencode_start_task and opencode_wait_for_task, allowing for parallel execution of multiple investigations. It supports running tasks in a shared directory or within isolated managed Git worktrees to keep source changes organized. The system provides detailed usage reporting, including metrics broken down by provider and model, to help track the economics of delegated sessions.
What you can do with it
- 1Parallel task executionDispatch multiple investigation or implementation tasks in parallel without blocking the orchestrator.
- 2Context window preservationAvoid polluting your primary agent's context with large file reads or extensive search outputs.
- 3Iterative subagent debuggingSend follow-up prompts to an existing task session to perform iterative back-and-forth work with a subagent.
Written from the project's README. Every use case is checked against a quote from it.
How to install OpenCode MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall OpenCode MCP in Claude Code
$ claude mcp add opencode-mcp -- npx -y mcp-server-opencodeInstall OpenCode MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"opencode-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}Install OpenCode MCP in VS Code
.vscode/mcp.json
{
"servers": {
"opencode-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}Install OpenCode MCP in VS Code CLI
$ code --add-mcp '{"name":"opencode-mcp","type":"stdio","command":"npx","args":["-y","mcp-server-opencode"]}'Install OpenCode MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"opencode-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}Install OpenCode MCP in Codex
$ codex mcp add opencode-mcp -- npx -y mcp-server-opencodeInstall OpenCode MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.opencode-mcp] command = "npx" args = ["-y", "mcp-server-opencode"]
Install OpenCode MCP in Gemini CLI
$ gemini mcp add -s user opencode-mcp npx -- -y mcp-server-opencodeInstall OpenCode MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"opencode-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-opencode"
]
}
}
}OpenCode MCP tools 10
Detected from the 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 | — |
Configuration
MCP_TOOL_TIMEOUTOPENCODE_MCP_SMOKE_MODEL
| Name | Description | |
|---|---|---|
| MCP_TOOL_TIMEOUT | — | |
| OPENCODE_MCP_SMOKE_MODEL | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablealejandro-technology/opencode-mcp is public and reachablegithub.com/alejandro-technology/opencode-mcp ↗Pass
- Package names this repository as its sourcemcp-server-opencode names alejandro-technology/opencode-mcp as sourcenpmjs.com/package/mcp-server-opencode ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-11-12github.com/alejandro-technology/opencode-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from mcp-server-opencodePass
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model10 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubopencode-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 questions
How do I add OpenCode MCP to Claude Code?
Run claude mcp add opencode-mcp -- npx -y mcp-server-opencode in your terminal. Add --scope user to make it available in every project.
How do I add OpenCode MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does OpenCode MCP provide?
It exposes 10 tools, including opencode_start_server, opencode_stop_server, opencode_list_agents, opencode_start_task, opencode_continue_task.
How does this server help with context window management?
It prevents context rot and bloat by delegating large file reads, extensive searches, and repetitive test runs to isolated subagents, returning only concise results to the lead agent.
Can I run multiple tasks at the same time?
Yes, task delegation is asynchronous, allowing you to dispatch multiple investigation or implementation tasks in parallel without blocking the orchestrator.
What are the system requirements for installation?
You need Node.js 18+ and OpenCode 1.x installed and configured on your PATH.