# Hoshin Kanri X-Matrix (npm · hoshin-kanri-mcp)

Strategic memory agents can build, score and keep current: a living X-Matrix with review cadences.

- Trust score: 70/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `hoshin.app`: 36/100, [markdown](https://verifymcp.io/servers/wellknownmcp-hoshin-kanri/hoshin.md), [page](https://verifymcp.io/servers/wellknownmcp-hoshin-kanri/hoshin)
- npm · `hoshin-kanri-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/wellknownmcp-hoshin-kanri/hoshin-kanri-mcp.md), [page](https://verifymcp.io/servers/wellknownmcp-hoshin-kanri/hoshin-kanri-mcp)

## Channel facts

- Registry: `npm`
- Package: `hoshin-kanri-mcp`
- Version: `3.0.0`
- 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**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), 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 (94 of 98), 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 (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1847 tokens (~131/item across 14 items; 14 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 wellknownmcp-hoshin-kanri -- npx -y hoshin-kanri-mcp
```

### Codex

```bash
codex mcp add wellknownmcp-hoshin-kanri -- npx -y hoshin-kanri-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add wellknownmcp-hoshin-kanri --command npx --arg -y --arg hoshin-kanri-mcp
```

### Hermes

```yaml
mcp_servers:
  wellknownmcp-hoshin-kanri:
    command: "npx"
    args: ["-y", "hoshin-kanri-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "wellknownmcp-hoshin-kanri": {
      "command": "npx",
      "args": [
        "-y",
        "hoshin-kanri-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.

### 2026-08-03 (score 70, +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 69, +7)

- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [functional regression] License: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-08-01 (score 62, −9)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 71, +65)

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

### 2026-07-30 (score 6, −41)

- [security regression] Malware scan: pass → unverified
- [security improvement] Source repository: fail → pass
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 2.0.1 → 3.0.0

### 2026-07-27 (score 47)

First indexed and scored.

## MCP tools (14)

### `add_idea` (~109 tokens)

Add a new idea to the Hoshin Kanri inbox. Ideas can be strategic initiatives, improvement suggestions, or action items that may later be linked to the X-Matrix.

Input parameters:

- `description` (string): Detailed description of the idea
- `priority` (string): Priority level (default: medium)
- `source` (string): Where this idea originated (default: conversation)
- `tags` (array): Tags for categorization
- `title` (string, required): Title of the idea (required)

### `list_objectives` (~91 tokens)

List strategic objectives from the X-Matrix. Can filter by quadrant (north=long-term objectives, east=annual objectives, south=actions/projects, west=KPIs).

Input parameters:

- `quadrant` (string): Which quadrant to list (default: all). North=strategic, East=annual, South=actions, West=KPIs
- `status` (string): Filter by status (default: all)

### `get_matrix_summary` (~49 tokens)

Get a summary of the current X-Matrix state including progress on objectives, key correlations, and attention items.

Input parameters:

- `include_correlations` (boolean): Include element correlations in response (default: true)

### `update_element_status` (~110 tokens)

Update the status or progress of a matrix element (objective, action, or KPI).

Input parameters:

- `element_id` (string, required): UUID of the element to update
- `external_ref` (string): Link to the matching project in the execution tool (Linear/Jira URL or ID). Set it once; weekly syncs use it to pull progress.
- `notes` (string): Update notes or comments
- `progress` (integer): Progress percentage (0-100)
- `status` (string): New status

### `search_ideas` (~91 tokens)

Search through the ideas inbox with filters for status, priority, tags, or text search.

Input parameters:

- `limit` (integer): Maximum results (default: 20)
- `priority` (string): Filter by priority
- `query` (string): Text search in title and description
- `status` (string): Filter by status (default: all)
- `tags` (array): Filter by tags (any match)

### `get_matrix_completeness` (~159 tokens)

Analyze X-Matrix completeness and get AI-friendly score. Returns:
\- Coverage: elements per quadrant (min 3-5 recommended)
\- Density: correlation fill rate between adjacent quadrants
\- Orphans: elements without any links
\- Chains: complete Vision→Objective→Initiative→KPI paths
\- Indicator Balance: checks if objectives/initiatives have both RESULT (lagging - measures outcomes like revenue, NPS) AND PERFORMANCE (leading - measures process like calls/week, % completion) indicators linked.

Ideal state: each objective and initiative should be linked to at least one result indicator AND one performance indicator.

Input parameters:

- `matrix_id` (string): UUID of the matrix to analyze (optional, uses default matrix if not provided)

### `get_matrix_data` (~139 tokens)

Get the COMPLETE dataset of an X-Matrix in one call: every element of all four quadrants (id, title, status, progress, externalRef, indicator type), all correlations (from/to element ids and titles, strength), and the completeness score.

Use this instead of get_matrix_summary when you need the full matrix — typically to render a view or build an interactive artifact (e.g. an X-Matrix cockpit for a leadership meeting, shareable with the team). The matrix_artifact prompt shows the recommended artifact layout.

Input parameters:

- `matrix_id` (string): UUID of the matrix (optional, uses the first active matrix if not provided)

### `share_matrix` (~271 tokens)

Publish a matrix as a public read-only web page and return the tokenized link — or list/revoke existing share links.

Publication is a deliberate act: anyone with the link can view the matrix (title, elements, correlations, completeness score) until the link is revoked or expires. The page is never indexed by search engines. Use it to share the X-Matrix with people OUTSIDE the organization (board members, investors, partners) without creating accounts. For sharing inside a claude.ai Team organization, prefer the matrix_artifact prompt instead.

Not available in local JSON mode (sovereign mode has no cloud page by design — export a snapshot artifact instead).

Input parameters:

- `action` (string): create (default): publish and return the link. list: existing shares with status. revoke: kill a link (requires share_id).
- `expires_in_days` (integer): Optional auto-expiry in days (default: no expiry, revocable manually)
- `label` (string): Optional label to remember who this link was created for (e.g. "board Q3")
- `matrix_id` (string): UUID of the matrix (optional, uses the first active matrix if not provided)
- `share_id` (string): UUID of the share to revoke (required for action=revoke, from action=list)

### `get_management_architecture` (~70 tokens)

Returns the complete management system architecture - all meeting cadences organized by hierarchy level (strategic, tactical, operational_mgmt, team_mgmt, execution). Shows the tree of meetings, their frequency, team scope, tracked quadrants, and how they cascade from strategic reviews down to daily stand-ups.

### `diagnose_theme_deployment` (~76 tokens)

Analyze if a strategic theme is properly deployed from vision down to operational meetings. Returns a deployment score, coverage per hierarchy level, and suggestions for improving deployment.

Input parameters:

- `theme_id` (string): UUID of the strategic theme to analyze
- `theme_name` (string): Name of the theme to search for (alternative to theme_id)

### `suggest_meeting_for_topic` (~76 tokens)

Recommend the right meeting level and cadence for a given topic based on its nature and the X-Matrix quadrant it relates to.

Input parameters:

- `element_id` (string): UUID of the X-Matrix element related to this topic (optional)
- `topic` (string, required): Description of the topic to find the right meeting for (required)

### `create_matrix` (~156 tokens)

Create a new X-Matrix. Use this to start a strategy from scratch: create the matrix, then add elements with upsert_element and wire them with set_correlation. The first matrix of an organization becomes the default one.

Input parameters:

- `description` (string): What this deployment covers
- `is_default` (boolean): Make this the default matrix of the organization
- `name` (string, required): Name of the matrix, e.g. "Strategy 2027" (required)
- `period_end` (string): End of the period, ISO date (YYYY-MM-DD)
- `period_start` (string): Start of the period, ISO date (YYYY-MM-DD)
- `period_type` (string): Planning horizon (default: annual)

### `upsert_element` (~301 tokens)

Create an X-Matrix element, or update one when element_id is given. Quadrants: north = 3-5 year vision, east = annual objectives, south = initiatives, west = KPIs. A west element should carry indicator_type so the completeness score can judge the leading/lagging balance.

Input parameters:

- `current_value` (string): Where it stands today, e.g. "31"
- `description` (string): Longer description, rationale, scope
- `element_id` (string): UUID of an existing element to update. Omit to create a new one.
- `external_ref` (string): URL or key of the project implementing this in your execution tool (Linear, Jira, GitHub)
- `indicator_type` (string): For west elements only: result = lagging (measures outcomes), performance = leading (measures the process producing them). Every objective should be tracked by at least one of each.
- `matrix_id` (string): UUID of the matrix (default: the organization default matrix)
- `quadrant` (string): Quadrant of the element (required when creating)
- `status` (string): Status of the element (default: active)
- `target_value` (string): Target to reach, e.g. "38"
- `title` (string): Title of the element (required when creating)
- `unit` (string): Unit of the values, e.g. "%", "k€", "days"

### `set_correlation` (~149 tokens)

Wire two elements of adjacent quadrants together, or unwire them with strength "none". Only adjacent pairs carry meaning: north↔east, east↔south, south↔west, north↔west. That constraint is what makes the matrix a deployment tool — a vision reaches a KPI through an objective and an initiative, never directly.

Input parameters:

- `from_element_id` (string, required): UUID of the first element (required)
- `matrix_id` (string): UUID of the matrix (default: the organization default matrix)
- `strength` (string, required): How strongly they are linked. "none" removes the correlation.
- `to_element_id` (string, required): UUID of the second element (required)

## Diagnostics

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

## Score history

- 2026-08-03: 70
- 2026-08-02: 69
- 2026-08-01: 62
- 2026-07-31: 71
- 2026-07-30: 6
- 2026-07-28: 47
- 2026-07-27: 47

## Links

- npm package: https://www.npmjs.com/package/hoshin-kanri-mcp
- Socket report: https://socket.dev/npm/package/hoshin-kanri-mcp
- Repository: https://github.com/wellknownmcp/hoshin-kanri
- Website: https://hoshin.app/
- Changelog RSS feed: https://verifymcp.io/servers/wellknownmcp-hoshin-kanri/hoshin-kanri-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/wellknownmcp-hoshin-kanri/hoshin-kanri-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/wellknownmcp-hoshin-kanri/hoshin-kanri-mcp