Hoshin Kanri — MCP server
The MCP server behind hoshin.app: a living X-Matrix your AI agent can read, challenge and update — 3-to-5-year objectives, annual objectives, initiatives, KPIs, the correlations between them, the review cadences that keep them alive, and a completeness score that gives a verdict instead of a vibe.
11 tools · 9 guided prompts · 3 transports · MIT.
Registry entry: io.github.wellknownmcp/hoshin-kanri
· npm: hoshin-kanri-mcp
Why this exists
Agents are good at doing the work and bad at knowing which work matters. The missing piece is not more memory — it is structured strategic memory: an object with quadrants, correlations and a score, so an agent can answer "does this initiative actually serve a stated objective?" and be wrong out loud when it does not.
That object is the X-Matrix, a Hoshin Kanri artifact that predates all of this by forty years. This server exposes it over the Model Context Protocol.
Install
Sovereign local mode — nothing leaves your machine
Your matrix lives in plain JSON files on your own disk. No account, no cloud, no telemetry. This is the default binary of the npm package, on purpose.
{
"mcpServers": {
"hoshin-kanri": {
"command": "npx",
"args": ["-y", "hoshin-kanri-mcp"],
"env": { "HOSHIN_DATA_DIR": "/path/to/your/data" }
}
}
}
HOSHIN_DATA_DIR defaults to ~/hoshin-data/. The files are the export:
readable, diffable, versionable, yours. See docs/data-residency.md.
Hosted mode — OAuth 2.1, nothing to install
claude.ai, Claude Desktop and Cursor connect straight to https://hoshin.app/mcp.
Dynamic client registration + PKCE, so there is no token to paste and no
config file to edit — add the URL as a connector and authorize.
Or with a static API token, over stdio
{
"mcpServers": {
"hoshin-kanri": {
"command": "npx",
"args": ["-y", "-p", "hoshin-kanri-mcp", "hoshin-kanri-mcp-remote"],
"env": { "AUTH_TOKEN": "hk_..." }
}
}
}
What is in here
| Path | What |
|---|---|
mcp-server/index-local.js | stdio transport, local JSON store — the npm default bin |
mcp-server/index-stdio.js | stdio transport against the hosted API |
mcp-server/index-streamable-http.js | Streamable HTTP transport, the one serving hoshin.app/mcp |
mcp-server/lib/tool-definitions.js | the 11 tool schemas, shared by all three transports |
mcp-server/lib/prompt-definitions.js | the 9 guided prompts, shared by all three transports |
mcp-server/lib/completeness.js | the completeness score, as pure functions |
mcp-server/lib/json-store.js | atomic local JSON store (tmp + rename, in-process mutex) |
docs/completeness-score.md | the score specification — metrics, weights, response shape |
docs/data-residency.md | where your strategy lives, per transport |
server.json | the MCP registry manifest |
Tool and prompt definitions are shared across transports by design: only the handlers differ. A tool that exists in hosted mode and not in local mode would quietly make the sovereign mode a second-class citizen, so parity is a rule, not an aspiration — with one deliberate exception, documented below.
Tools
get_matrix_data · get_matrix_summary · get_matrix_completeness ·
list_objectives · update_element_status · add_idea · search_ideas ·
get_management_architecture · diagnose_theme_deployment ·
suggest_meeting_for_topic · share_matrix
Two worth calling out:
get_matrix_completenessreturns a 0–100 score across five metrics (coverage, correlation density, orphan elements, end-to-end strategic chains, leading/lagging indicator balance) with the specific suggestions behind it. This is the part that makes an agent useful rather than agreeable.update_element_statusaccepts anexternal_ref— the URL or key of the Linear/Jira/GitHub project implementing that initiative. Strategy lives here, tasks live in your execution tool, and theweekly_syncprompt walks an agent across both.
share_matrix publishes a revocable, read-only public page of a matrix. It is
refused in local mode — by design: in sovereign mode there is no cloud for
your data to leak into, so there is nothing to publish from.
Prompts
weekly_sync (pull execution progress from your issue tracker's MCP, update
statuses, prepare the weekly agenda) · matrix_artifact (a boardroom-ready
interactive X-Matrix) · strategic_review · deployment_diagnosis ·
indicator_balance · meeting_setup_guide · visual_matrix · export_data ·
idea_triage
Development
cd mcp-server
pnpm install
pnpm start:local # sovereign JSON mode
pnpm start:stdio # hosted API mode (AUTH_TOKEN, API_BASE_URL)
pnpm start # Streamable HTTP (server-side; MCP_PORT, API_BASE_URL, OAUTH_ISSUER)
Smoke-test the local transport without any client:
printf '%s\n' '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"smoke","version":"1"}}}' \
| HOSHIN_DATA_DIR=/tmp/hoshin-smoke node index-local.js 2>/dev/null
stdout carries JSON-RPC only; logs and the startup banner go to stderr.
This repository holds the MCP server and its specifications. The hosted web application (Next.js, Prisma, the OAuth 2.1 authorization server) is a separate, closed codebase — the MIT code here is what you run, and what you can audit before running it.
Issues and pull requests are welcome, in English or French.
Learn more
MIT — the code is a commodity; your strategy is not.