Skip to main content
Glama

KanseiLink Cockpit

cockpit-mcp MCP Server

Monorepo for @kansei-link/cockpit — an MCP server for Japanese accounting workflow automation.

Packages

Package

Description

Status

packages/cockpit-mcp

MCP server — two-stage classifier + TaxRuleEngine

✅ npm

packages/cockpit-dashboard

Web dashboard (coming soon)

🚧

Related MCP server: financial-law-mcp

Quick Start

npm install @kansei-link/cockpit

See packages/cockpit-mcp/README.md for setup and configuration.

Data

The data/ directory contains classification rules used by the MCP server:

  • keyword-dict/ — Keyword dictionary for 19-category classification

  • exclusion-rules/ — Patterns to exclude non-classifiable transactions

  • tax-rules/ — Consumption tax rates, withholding rules, invoice system config

License

MIT — see LICENSE for details.

Copyright (c) 2026 Synapse Arrows PTE. LTD.

Available Tools

12 tools
check_duplicateA

Check if a transaction already exists in freee (= by date + amount + memo prefix). Use BEFORE register to prevent double-posting.

Inputs: date (required), memo (required), amount (required).

check_exclusionB

7-rule exclusion check for Japanese accounting. Returns excluded:true if transaction should NOT be auto-journalized. Rules: 内容不明デビット / 借入金返済 / 社保税金 / 給与支払い / 投資 / ATM出金 / 公共料金.

Inputs: memo (required), amount (required), employees, partner_name.

classify_transactionA

Two-stage classifier for Japanese tax accounting. Stage 1: keyword dictionary match (14 categories × ~50 keywords). Stage 2 (= deferred to Phase 1.B): Claude API fallback. Returns 勘定科目 + 税区分 + confidence.

Inputs: date (required), memo (required), amount (required), partner_name.

correct_classificationA

税理士修正フィードバック。誤分類を記録し、同パターンの取引が今後来たら修正後の勘定科目を自動適用。Linksee Memory caveat layer と同等(= 永続記憶、二度と同じ誤りをしない)。修正は全社共通 or 特定会社のみに適用可能。

Inputs: reason (required), memo_pattern (required), to_category_id (required), to_category_name_ja (required), +4 more.

generate_monthly_reportA

Generate a monthly review report. Takes transaction data (from freee API or CSV import), classifies all transactions, detects anomalies, and produces a structured Markdown report with category breakdown, anomaly alerts, and review items. Designed for tax accountants to present to clients.

Inputs: month (required), format, use_freee, company_name, +3 more.

import_csvA

Import CSV from 弥生会計/freee/MoneyForward or generic format. Auto-detects source format from headers. Runs each transaction through the full classification pipeline (Stage 0 exclusion → Stage 1+2 classification → confidence routing). Returns categorized results + review queue + Markdown report. 弥生 users: export 仕訳日記帳 as UTF-8 CSV.

Inputs: csv_content (required), source, date_column, memo_column, +2 more.

list_freee_companiesA

List all companies (事業所) accessible by the configured freee OAuth token. Returns company IDs + names. Used for multi-company batch processing.

Inputs: no named parameters.

list_freee_dealsB

List transactions (取引) from freee API for the configured company. Useful for sync + classification dogfood.

Inputs: type, limit, offset, end_issue_date, +1 more.

nightly_runA

Nightly batch pipeline. Processes ALL companies accessible by the token (= multi-company batch). Pipeline per company: fetch unprocessed (status=unsettled) → Stage 0 exclusion → Stage 1+2 classify → confidence routing (high=auto, medium=auto+log, low=human_review) → aggregate summary. Currently dry-run only (write-back pending Phase 1.B).

Inputs: dry_run, period_end, company_ids, concurrency, +2 more.

recall_memoryB

過去の分類パターン・修正履歴を検索。取引の摘要/取引先から過去パターンを参照し、分類結果の根拠を確認。Memory stats(pattern hit率等)の確認にも使用。

Inputs: memo, amount, show_stats, partner_name, +1 more.

reconcile_cross_saasC

Cross-SaaS reconciliation (= freee ↔ MF). Currently freee-only mode (= MF connector pending Phase 1.B). Detects duplicate fingerprints within freee.

Inputs: period_end (required), period_start (required).

upsert_partnerA

取引先マスタ auto-creation in freee. Fuzzy match against existing partners; if new, create. Returns partner_id.

Inputs: partner_name (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 12 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: duplicate detection, exclusion checks, classification, correction, reporting, import, listing companies and deals, batch processing, memory recall, reconciliation, and partner management. No two tools overlap in functionality.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (check_duplicate, classify_transaction, import_csv, etc.), but 'nightly_run' is an exception (adjective_noun) that slightly breaks consistency. Overall, the naming is clear and predictable.

    Tool Count5/5

    12 tools is well-scoped for an accounting automation server, covering all major steps from import to classification to reporting without being excessive or insufficient.

    Completeness5/5

    The tool set provides complete coverage of the intended workflow: import, duplicate detection, exclusion rules, classification, correction feedback, multi-company batch processing, report generation, memory recall, and reconciliation. No obvious gaps.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      MCP server for DACH accounting automation. Connect AI assistants to sevDesk and Lexoffice — create invoices, manage contacts, handle bookings and vouchers for German-speaking businesses.
      15
      55 npm
      -
    • A
      license
      A
      quality
      D
      maintenance
      MCP server to fetch Japanese financial laws and regulations from the e-Gov API, preventing hallucinations in Claude's responses. Supports 9 domains including Financial Instruments and Exchange Act, Banking Act, etc.
      5
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Multi-tenant MCP server connecting accounting software to AI assistants via ~87 tools. Supports Bokio (Swedish accounting) with mock mode for development.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that connects AI agents to 34,500+ Australian Taxation Office documents, providing cited answers, tax deduction discovery, depreciation scheduling, BAS checklists, and audit risk assessment through 13 specialized tools.
      19
      AGPL 3.0