hoshin-kanri
A living X-Matrix your AI agent can read, challenge and update — 3-to-5-year objectives, annual objectives, initiatives, KPIs, correlations, review cadences, and a completeness score. Exposes 11 tools and 9 guided prompts over MCP with local or hosted transports.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
wellknownmcp
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
add_ideaAdd 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.
list_objectivesList strategic objectives from the X-Matrix. Can filter by quadrant (north=long-term objectives, east=annual objectives, south=actions/projects, west=KPIs).
get_matrix_summaryGet a summary of the current X-Matrix state including progress on objectives, key correlations, and attention items.
update_element_statusUpdate the status or progress of a matrix element (objective, action, or KPI).
search_ideasSearch through the ideas inbox with filters for status, priority, tags, or text search.
get_matrix_completenessAnalyze 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: ch…
get_matrix_dataGet 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…
share_matrixPublish 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 …
get_management_architectureReturns 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…
diagnose_theme_deploymentAnalyze 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.
suggest_meeting_for_topicRecommend the right meeting level and cadence for a given topic based on its nature and the X-Matrix quadrant it relates to.
create_matrixCreate 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.
upsert_elementCreate 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.
set_correlationWire 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 …
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
express vulnerable to XSS via response.redirect()
Express.js Open Redirect in malformed URLs
API_BASE_URLnpm package. Env: MCP_PORT, , OAUTH_ISSUER.AUTH_TOKENHOSHIN_DATA_DIRdefaults to ~/hoshin-data/. Files are plain JSON —MCP_PORTnpm package. Env: , API_BASE_URL, OAUTH_ISSUER.MCP_SESSION_IDLE_MSMCP_SESSION_SWEEP_MSOAUTH_ISSUERnpm package. Env: MCP_PORT, API_BASE_URL, .Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
14/14 tools missing one or more hints — add_idea (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_objectives (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_matrix_summary (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/wellknownmcp/hoshin-kanri)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check