KonMari MCP Server
Connector for pulling pages and content from Confluence as a source in the data inventory, so wiki content can be categorised, scored, deduplicated and exposed to agents through the read-only MCP server.
Connector for registering Google Drive files and folders as sources, allowing their contents to be scanned, chunked, metadata-enriched and made queryable by agents via the MCP server.
Connector for ingesting files and folder structures from a Nextcloud instance as a data source, feeding them into the KonMari pipeline (inventory, joy-test scoring, deduplication, normalisation) so the tidied, owner-tagged results can be served to agents.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MarieKondo­ForAgents
Make your organisation's data agent-ready, the KonMari way.
English · Deutsch
Point an AI agent at a SharePoint, a CRM and a file share and it finds
angebot_final_v3(2).docx, three price lists from three years and a customer table nobody has
touched since 2021. Then it answers confidently and wrongly.
The KonMari-Kit fixes the data, not the prompt. It takes one use case, discards what doesn't belong, sorts the rest by category, gives every item an owner, a definition and the right permissions, and serves the result to your agents through a read-only MCP server. Every step is gated, every decision is made by a named person and logged, and every change can be undone.
Quick start with Claude Code
/plugin marketplace add KI-Klub-Werder-e-V/MarieKondoForAgents
/plugin install konmari@konmari-kitOpen Claude Code in an empty folder and say what you need:
Tidy our data for an FAQ agent in the club office.
Claude interviews you for the charter, registers your sources, runs the scans and checks, and
explains each report. It stops before every approval and asks the person the charter names.
Requires Python 3.12 and uv. Details: docs/agents.md.
git clone https://github.com/KI-Klub-Werder-e-V/MarieKondoForAgents
cd MarieKondoForAgents && uv sync
cd examples/verein-faq-assistant # fictional sports club, FAQ assistant
uv run konmari next # where are we, what's next
uv run konmari charter validate
uv run konmari charter approve --as anna
uv run konmari metrics validate
uv run konmari metrics approve --as ben
uv run konmari charter gate --step inventoryThe gate refuses until every must-have metric has a baseline:
unmet: metrics: must_have metric 'answer_accuracy' has no baseline or measurement planContinue with the guide. All commands: docs/cli.md.
Related MCP server: governed-mcp
How it works
Nine steps for one use case. Each step checks that the previous one is done.
# | Step | Commands | What happens |
1 | Commit |
| Use case, roles, GDPR/AI Act screening, success metrics with baselines |
2 | Gather by category |
| Sources across systems, grouped by category instead of location, ordered by risk |
3 | Spark joy? |
| Six-question test per asset, proposal keep / fix / discard |
4 | Discard first |
| Duplicates, superseded versions, off-scope items to a reversible archive |
5 | One truth |
| Dates, IDs and names normalised, entities matched, a leading source per field |
6 | Fold |
| Structure-aware chunks, metadata on every chunk, approved business glossary |
7 | Secure |
| Source permissions carried into the index, PII masked, hash-chained audit trail |
8 | Connect |
| Versioned data products and a read-only MCP server |
9 | Check |
| Golden questions with citations and abstention, freshness and drift alerts |
Low-risk categories go first (public FAQ), special-category personal data last.
The joy test
Every asset is scored 0–3 on six criteria, with evidence:
Criterion | Checked against |
Authoritative and current | last change vs. agreed update frequency, superseded versions |
Owned | a named owner who maintains it |
Meaning clear | columns and terms defined in the glossary |
Retrievable | well-cut passages, clean table schemas |
Conflicts resolved | a rule for which source wins |
Permissions explicit | source ACLs present and propagated |
Before | After | |
Format | whole documents, raw tables | chunked passages, versioned data products |
Metadata | file name | source, date, owner, freshness, definitions |
Access | whatever the service account sees | read scopes per agent, source permissions kept |
Consistency | duplicates, three versions of the truth | deduplicated, one leading source per field |
Freshness | manual, forgotten | scheduled refresh with change tracking |
Discoverability | buried in silos | catalogued and callable via MCP |
Features
Deterministic engine. Gates, scoring, deduplication and policies are rules with versioned thresholds. Same inputs, same result. Models are optional and pinned.
Humans approve. Discarding, masking, erasing and publishing need sign-off from the role the charter names, recorded with identity and time.
Reversible and auditable. Archive instead of delete, restore by command, a hash-chained audit trail you can verify with
konmari audit verify.Duplicates at three levels. Identical files, near-duplicates (MinHash/LSH), semantic duplicates (embeddings, optional).
GDPR built in. Local PII detection (Presidio, spaCy), retention rules and legal holds per category, keyed pseudonymisation, record of processing activities export.
Open standards. DCAT inventory, OpenLineage lineage, ODPS/ODCS data products, SKOS glossary, MCP for agents.
Self-hosted. DuckDB locally, Postgres 16 in production. No cloud service required.
Documentation
Step-by-step guide |
|
Command reference | |
Claude Code skill | |
Specs and roadmap | |
Research with sources |
Contributing
The most useful contribution is a pilot report: which use case, which systems, how far you got and where it got stuck. Connectors (Nextcloud, Confluence, Google Drive, more CRMs), examples and translations are welcome too.
uv sync && uv run pytest -q
openspec validate --all --strictBehaviour changes start as an OpenSpec change. See
CONTRIBUTING.md and AGENTS.md.
License
Apache-2.0. A project of KI Klub Werder e. V.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
AI-native data layer: sheets, databases and apps for every agent, with exact answers and audit.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Governed access to sensitive data, secrets and APIs for AI agents. A signed proof for each decision.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query governed data warehouses through plain language, returning grounded answers with SQL, confidence grades, and signed receipts while enforcing access, testing, and audit controls.159 PyPI18Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query a read-only data surface through typed tools, enforcing caller-specific row access, field masking, and withheld-row disclosure so they can retrieve entitled information without writes or silent data leakage.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query DuckDB, Postgres, and BigQuery through a governed, read-only layer with a semantic model, SQL guard, role-based row policies, PII pseudonymization, audit logging, and cost caps.40 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceGives AI agents governed context about a data warehouse — table meaning, ownership, lineage, freshness, and PII flags — plus read-only, row-limited, PII-protected querying across DuckDB, Snowflake, and Databricks. Guardrails enforced at parsing, connection, and result layers keep agents from writing, running away, or leaking personal data.86 PyPIMIT