# io.github.wundam/orchex (npm · @wundam/orchex)

Autopilot AI orchestration — auto-plan, parallelize, self-heal, and route across 6 LLMs.

- Trust score: 62/100 (medium)
- Change this week: +46
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-07

## Components

- npm · `@wundam/orchex`: 62/100 (this document), [markdown](https://verifymcp.io/servers/wundam-orchex/wundam-orchex.md), [page](https://verifymcp.io/servers/wundam-orchex/wundam-orchex)

## Channel facts

- Registry: `npm`
- Package: `@wundam/orchex`
- Version: `1.0.0-rc.11`
- 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 2026-08-07.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Known CVEs were checked across the 115 of 119 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 115 of 119 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 6/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (BUSL-1.1) isn't a recognized OSI-approved license.
  - Actively maintained (last published 94 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1112 tokens (~92/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 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 wundam-orchex -- npx -y @wundam/orchex
```

### Codex

```bash
codex mcp add wundam-orchex -- npx -y @wundam/orchex
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add wundam-orchex --command npx --arg -y --arg @wundam/orchex
```

### Hermes

```yaml
mcp_servers:
  wundam-orchex:
    command: "npx"
    args: ["-y", "@wundam/orchex"]
```

### Other

```json
{
  "mcpServers": {
    "wundam-orchex": {
      "command": "npx",
      "args": [
        "-y",
        "@wundam/orchex"
      ]
    }
  }
}
```

## 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.

### 2026-08-07 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-04 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-03 (score 60, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 57, +57)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] License: unverified → fail
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: BUSL-1.1

### 2026-08-01 (score 0, −16)

- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 16, −24)

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

### 2026-07-28 (score 40, +22)

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

### 2026-07-27 (score 18)

First indexed and scored.

## MCP tools (12)

### `init` (~74 tokens)

Initialize Orchestration

Initialize a new orchestration for a feature. Creates .orchex/active/manifest.yaml with streams.

Input parameters:

- `feature` (string, required): Feature name (e.g., "user-authentication")
- `project_dir` (string): Project directory (defaults to cwd)
- `streams` (object, required): Map of stream ID → stream definition

### `add_stream` (~134 tokens)

Add Stream

Add a new stream to the active orchestration.

Input parameters:

- `deps` (array): Stream IDs this depends on
- `id` (string, required): Unique stream ID
- `name` (string, required): Human-readable stream name
- `owns` (array): File paths this stream owns
- `plan` (string): Implementation plan for the stream
- `project_dir` (string): Project directory
- `reads` (array): File paths this stream needs to read (but does not own)
- `setup` (array): Setup commands to run before the stream executes
- `verify` (array): Verification commands to run after the stream completes

### `status` (~26 tokens)

Orchestration Status

Get the current orchestration status and progress.

Input parameters:

- `project_dir` (string): Project directory

### `execute` (~179 tokens)

Execute Orchestration

Run the orchestration. Each call executes one wave of streams in parallel via LLM API, applies artifacts to the codebase, and runs verification commands. Call repeatedly for each wave, or use auto mode.

Input parameters:

- `dry_run` (boolean): Preview without executing (default: false)
- `iterate` (boolean): When true with mode=auto, re-plan and re-execute if failures remain. Max 3 iterations.
- `max_iterations` (number): Maximum iterations for iterative mode (default: 3, max: 5).
- `mode` (string): auto: execute all waves sequentially. wave: execute one wave and return.
- `model` (string): LLM model override (auto-detected based on provider)
- `project_dir` (string): Project directory
- `wave` (number): Run a specific wave number (optional)

### `complete` (~54 tokens)

Complete

Mark a stream as complete, or archive the entire orchestration.

Input parameters:

- `archive` (boolean): Archive the orchestration
- `project_dir` (string): Project directory
- `stream_id` (string): Stream ID to mark complete

### `recover` (~108 tokens)

Recover Stuck Streams

Recover streams stuck in in_progress state or failed state. Auto-detects stuck streams and resets them to pending for retry, or skips them.

Input parameters:

- `include_failed` (boolean): Also recover failed streams (not just stuck in_progress ones).
- `mode` (string): retry: reset stuck streams to pending. skip: mark them as skipped.
- `project_dir` (string): Project directory
- `stream_id` (string): Specific stream ID to recover. If omitted, recovers all stuck streams.

### `learn` (~145 tokens)

Learn from Plan

Parse a planning document and generate stream definitions. Returns proposed streams for review before initialization.

Input parameters:

- `deliverable_level` (number): Header level for deliverables (2=H2, 3=H3)
- `document_content` (string): Plan document contents as string. When provided, used instead of reading document_path from disk. Useful for cloud mode where the server cannot access local files.
- `document_path` (string, required): Path to the markdown planning document
- `prefix` (string): Optional prefix for stream IDs
- `project_dir` (string): Project directory (for resolving relative paths)
- `validate_antipatterns` (boolean): Validate generated streams against anti-patterns

### `init-plan` (~103 tokens)

Generate Plan Template

Generate an annotated markdown plan template that teaches users how to structure documents for orchex learn. Creates a starter plan file with inline comments explaining what the learn pipeline parses.

Input parameters:

- `feature_name` (string): Feature name for the plan (used in title and example stream IDs)
- `output_path` (string): Output file path. Defaults to docs/plans/YYYY-MM-DD-<feature>-plan.md
- `project_dir` (string): Project directory (defaults to cwd)

### `auto` (~158 tokens)

Auto-Orchestrate

Generate a plan from user intent, preview streams, and optionally execute. Flow: gather context → LLM generates plan → learn pipeline → preview → approve → execute → report.

Input parameters:

- `approve` (boolean): If true, execute immediately after preview. If false (default), return preview only.
- `approved_streams` (array): Stream IDs to approve for execution. Non-listed pending streams will be skipped. Omit this parameter to approve all streams (default behavior).
- `intent` (string, required): What you want to build (e.g., "Add user authentication with JWT")
- `model` (string): LLM model override
- `project_dir` (string): Project directory (defaults to cwd)
- `provider` (string): LLM provider override

### `reset-learning` (~66 tokens)

Reset Learning

Reset learning data: thresholds, events, patterns, and/or reports.

Input parameters:

- `confirm` (boolean, required): Must be true to proceed
- `patterns_only` (boolean): Only reset patterns
- `project_dir` (string): Project directory
- `reports_only` (boolean): Only reset reports

### `rollback-stream` (~42 tokens)

Rollback Stream

Revert file changes made by a specific stream using git.

Input parameters:

- `project_dir` (string): Project directory
- `stream_id` (string, required): Stream ID to rollback

### `reload` (~23 tokens)

Reload MCP Server

Restart the MCP server to pick up rebuilt code. MCP client will reconnect automatically.

## Diagnostics

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

## Score history

- 2026-08-07: 62
- 2026-08-06: 61
- 2026-08-05: 61
- 2026-08-04: 61
- 2026-08-03: 60
- 2026-08-02: 57
- 2026-08-01: 0
- 2026-07-31: 16
- 2026-07-30: 40
- 2026-07-28: 40
- 2026-07-27: 18

## Links

- npm package: https://www.npmjs.com/package/@wundam/orchex
- Socket report: https://socket.dev/npm/package/@wundam/orchex
- Changelog RSS feed: https://verifymcp.io/servers/wundam-orchex/wundam-orchex.xml
- Changelog JSON feed: https://verifymcp.io/servers/wundam-orchex/wundam-orchex.json
- HTML version of this page: https://verifymcp.io/servers/wundam-orchex/wundam-orchex