# io.github.xiaolai/claude-octopus (npm · claude-octopus)

Spawn multiple specialized Claude Code agents as MCP servers, each independently configured.

- Trust score: 67/100 (medium)
- Change this week: +43
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `claude-octopus`: 67/100 (this document), [markdown](https://verifymcp.io/servers/xiaolai-claude-octopus/claude-octopus.md), [page](https://verifymcp.io/servers/xiaolai-claude-octopus/claude-octopus)

## Channel facts

- Registry: `npm`
- Package: `claude-octopus`
- Version: `1.1.10`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (107 of 111), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (107 of 111), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (ISC).
  - Actively maintained (last published 46 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 728 tokens (~145/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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add xiaolai-claude-octopus -- npx -y claude-octopus
```

### Codex

```bash
codex mcp add xiaolai-claude-octopus -- npx -y claude-octopus
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add xiaolai-claude-octopus --command npx --arg -y --arg claude-octopus
```

### Hermes

```yaml
mcp_servers:
  xiaolai-claude-octopus:
    command: "npx"
    args: ["-y", "claude-octopus"]
```

### Other

```json
{
  "mcpServers": {
    "xiaolai-claude-octopus": {
      "command": "npx",
      "args": [
        "-y",
        "claude-octopus"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 66, +46)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] License: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: ISC

### 2026-07-31 (score 20, −7)

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

### 2026-07-30 (score 27, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-28 (score 45, +21)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: unverified
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100

### 2026-07-27 (score 24)

First indexed and scored.

## MCP tools (5)

### `claude_code` (~293 tokens)

Send a task to an autonomous Claude Code agent. It reads/writes files, runs shell commands, searches codebases, and handles complex software engineering tasks end-to-end. Returns the result text plus a session_id for follow-ups via claude_code_reply.

Input parameters:

- `additionalDirs` (array): Extra directories the agent can access for this invocation
- `cwd` (string): Working directory (overrides CLAUDE_CWD)
- `disallowedTools` (array): Additional tools to block (unions with server-level blacklist)
- `effort` (string): Thinking effort override
- `maxBudgetUsd` (number): Max spend in USD
- `maxTurns` (integer): Max conversation turns
- `model` (string): Model override (e.g. "sonnet", "opus", "haiku")
- `permissionMode` (string): Permission mode override (can only tighten, never loosen)
- `plugins` (array): Additional plugin paths to load for this invocation (unions with server-level plugins)
- `prompt` (string, required): Task or question for Claude Code
- `run_id` (string): Workflow run ID — groups related agent calls into one timeline. Auto-generated if omitted; returned in every response for propagation.
- `systemPrompt` (string): Additional system prompt (appended to server default)
- `tools` (array): Restrict available tools to this list (intersects with server-level restriction)

### `claude_code_reply` (~138 tokens)

Continue a previous claude_code conversation by session ID. Use this for follow-up questions, iterative refinement, or multi-step workflows that build on prior context.

Input parameters:

- `cwd` (string): Working directory override
- `maxBudgetUsd` (number): Max spend in USD
- `maxTurns` (integer): Max conversation turns
- `model` (string): Model override
- `prompt` (string, required): Follow-up instruction or question
- `run_id` (string): Workflow run ID — pass the same run_id from the original call to keep entries grouped.
- `session_id` (string, required): Session ID from a prior claude_code response

### `claude_code_timeline` (~92 tokens)

Query the cross-agent workflow timeline. No args: list all runs. run_id: show one run's agent sequence. session_id: retrieve timeline entry and session metadata. Use claude_code_transcript for full transcripts.

Input parameters:

- `run_id` (string): Show all entries for this workflow run, ordered by time
- `session_id` (string): Retrieve timeline entry and session metadata for a specific session

### `claude_code_transcript` (~99 tokens)

Retrieve the full conversation transcript for a session from Claude Code's storage. Returns chronological user/assistant messages. Use session_id from a prior query or timeline lookup.

Input parameters:

- `include_system` (boolean): Include system messages (default: false)
- `limit` (integer): Maximum number of messages to return
- `offset` (integer): Skip this many messages from the start
- `session_id` (string, required): Session ID to retrieve transcript for

### `claude_code_report` (~106 tokens)

Generate a self-contained HTML report of a workflow run. No args: list all runs. run_id: detailed report for that run with agent sequence, cost breakdown, and collapsible transcripts. Save the returned HTML to a file and open in a browser.

Input parameters:

- `include_transcripts` (boolean): Include full session transcripts in run reports (default: true, requires session persistence)
- `run_id` (string): Generate detailed report for this run. Omit to list all runs.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/xiaolai-claude-octopus/claude-octopus#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 66
- 2026-08-01: 20
- 2026-07-31: 20
- 2026-07-30: 27
- 2026-07-28: 45
- 2026-07-27: 24

## Links

- npm package: https://www.npmjs.com/package/claude-octopus
- Socket report: https://socket.dev/npm/package/claude-octopus
- Repository: https://github.com/xiaolai/claude-octopus
- Changelog RSS feed: https://verifymcp.io/servers/xiaolai-claude-octopus/claude-octopus/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/xiaolai-claude-octopus/claude-octopus/changelog.json
- HTML version of this page: https://verifymcp.io/servers/xiaolai-claude-octopus/claude-octopus