# opencode subagents (npm · opencode-subagent-mcp)

Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.

- Trust score: 79/100 (medium)
- Change this week: +13
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-03

## Components

- npm · `opencode-subagent-mcp`: 79/100 (this document), [markdown](https://verifymcp.io/servers/sebstaq-opencode-subagent-mcp/opencode-subagent-mcp.md), [page](https://verifymcp.io/servers/sebstaq-opencode-subagent-mcp/opencode-subagent-mcp)

## Channel facts

- Registry: `npm`
- Package: `opencode-subagent-mcp`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-03.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to sebstaq/opencode-subagent-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 705 tokens (~141/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 48% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the opencode subagents MCP server?

opencode subagents runs locally as an npm package, launched with npx -y opencode-subagent-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add sebstaq-opencode-subagent-mcp -- npx -y opencode-subagent-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "sebstaq-opencode-subagent-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "opencode-subagent-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sebstaq-opencode-subagent-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "opencode-subagent-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add sebstaq-opencode-subagent-mcp -- npx -y opencode-subagent-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sebstaq-opencode-subagent-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "opencode-subagent-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sebstaq-opencode-subagent-mcp --command npx --arg -y --arg opencode-subagent-mcp
```

### Hermes

```yaml
mcp_servers:
  sebstaq-opencode-subagent-mcp:
    command: "npx"
    args: ["-y", "opencode-subagent-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "sebstaq-opencode-subagent-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "opencode-subagent-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add sebstaq-opencode-subagent-mcp -t stdio -c npx -a -y opencode-subagent-mcp
```

### Other

```json
{
  "mcpServers": {
    "sebstaq-opencode-subagent-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "opencode-subagent-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-02 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-30 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 77, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 76, +10)

- [security improvement] Known CVEs: unverified → pass
- [functional regression] Schema quality: 123 → 141
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Dependency health: unverified → 0.85
- [functional] Package version: 0.1.2 → 0.1.3

### 2026-09-26 (score 66)

First indexed and scored.

## MCP tools (5)

### `agent` (~364 tokens)

opencode subagent

Launch a subagent that runs on an opencode model (default opencode-go/deepseek-v4.1-flash) in the current project. Mirrors the built-in Agent tool: give a self-contained task prompt; the agent starts with no conversation context and returns only its final report. subagent_type accepts Claude agent definitions from .claude/agents/ (their prompt, tools, permissionMode and maxTurns apply) or opencode agents (general, explore, plan, build). isolation 'worktree' runs it in a temporary git worktree off the default branch, removed if unchanged. The call blocks until the agent finishes (it is backgrounded automatically after a while); set run_in_background to return at once and collect the result with wait.

Input parameters:

- `cwd` (string): Working directory (default: the project directory)
- `description` (string, required): Short (3-5 word) description of the task
- `disallowed_tools` (array)
- `effort` (string): Model variant/reasoning effort, e.g. low, high, max
- `isolation` (string)
- `max_turns` (integer)
- `model` (string): opencode model as provider/model (default: opencode-go/deepseek-v4.1-flash)
- `output_schema` (object): JSON Schema the final answer must satisfy; returned as structured output
- `permission_mode` (string): Permission mode (default: auto)
- `prompt` (string, required): The task for the agent to perform
- `run_in_background` (boolean)
- `subagent_type` (string): Claude agent definition name or opencode agent name (default: general)
- `tools` (array): Allowlist of tools (Claude or opencode names)

### `send_message` (~111 tokens)

Continue an opencode subagent

Send a follow-up message to a finished opencode subagent by agent_id. It resumes with its full previous history (and its worktree, if one was kept) and returns its new final report. Also works for agent_ids from before a restart of the MCP server or Claude Code session, and for agents that were interrupted by such a restart.

Input parameters:

- `agent_id` (string, required)
- `max_turns` (integer)
- `message` (string, required)
- `run_in_background` (boolean)

### `wait` (~54 tokens)

Wait for an opencode subagent

Wait for a background opencode subagent and return its result. agent_ids from before a restart of the MCP server still work.

Input parameters:

- `agent_id` (string, required)
- `timeout_seconds` (number): Return early if still running

### `stop` (~43 tokens)

Stop an opencode subagent

Abort a running opencode subagent. Returns what it produced so far. agent_ids from before a restart of the MCP server still work.

Input parameters:

- `agent_id` (string, required)

### `list` (~62 tokens)

List opencode subagents

List this session's opencode subagents and the available agent types. It shows agents started or used since this MCP server started; agents from before a restart are not listed but their agent_id still works with wait, send_message and stop.

Input parameters:

- `cwd` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/sebstaq-opencode-subagent-mcp/opencode-subagent-mcp#diagnostics

## Score history

- 2026-10-03: 79
- 2026-10-02: 79
- 2026-10-01: 78
- 2026-09-30: 78
- 2026-09-29: 77
- 2026-09-28: 77
- 2026-09-27: 76
- 2026-09-26: 66

## Common questions

### What is the opencode subagents MCP server?

opencode subagents is an MCP server listed in the public MCP registry as io.github.sebstaq/opencode-subagent-mcp. Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity. This page covers its npm package (opencode-subagent-mcp).

### Is the opencode subagents MCP server safe to use?

opencode subagents scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 3 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the opencode subagents MCP server expose?

opencode subagents exposes 5 tools: agent, send_message, wait, stop, list. Their descriptions and schemas cost roughly 634 tokens of context every time the server is loaded.

### Is the opencode subagents MCP server still maintained?

opencode subagents is still listed as active in the MCP registry. We last reached this channel on 3 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the opencode subagents MCP server under?

opencode subagents declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/opencode-subagent-mcp
- Socket report: https://socket.dev/npm/package/opencode-subagent-mcp
- Repository: https://github.com/sebstaq/opencode-subagent-mcp
- Changelog RSS feed: https://verifymcp.io/servers/sebstaq-opencode-subagent-mcp/opencode-subagent-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sebstaq-opencode-subagent-mcp/opencode-subagent-mcp.json
- HTML version of this page: https://verifymcp.io/servers/sebstaq-opencode-subagent-mcp/opencode-subagent-mcp