// SCAN REPORT

Cockpit

13 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

4 can modify or destroy data

9 read-only

13 tools total

Community server · catalogue entry verified 30/06/2026

How to control Cockpit ↓

TOOL MAP

What Cockpit exposes to your agents

Read (9) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Cockpit tools

Execute · High nightly_run This tool executes a complex, multi-company batch pipeline that automatically routes transactions through confidence-based decision logic and triggers downstream workflows (auto-approval, logging, human escalation). Write · High import_csv This tool ingests external data (CSV) and writes classified transaction records into the accounting system. Write · High upsert_partner The tool creates or updates partner records in a financial accounting system (freee). Write · High correct_classification This tool writes a persistent correction record that modifies future classification behavior globally or per-company.

4 of Cockpit's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Cockpit

PolicyLayer is an MCP gateway — it sits between your AI agents and Cockpit, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "correct_classification": {
    "limits": [
      {
        "counter": "correct_classification_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_duplicate": {
    "limits": [
      {
        "counter": "check_duplicate_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Cockpit — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON COCKPIT →

Instant setup, no code required.

FULL CATALOGUE

All 13 Cockpit tools

EXECUTE 1 tools

Execute nightly_run Nightly batch pipeline. Processes ALL companies accessible by the token (= multi-company batch). Pipeline per

WRITE 3 tools

Write correct_classification 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 o Write import_csv Import CSV from 弥生会計/freee/MoneyForward or generic format. Auto-detects source format from headers. Runs each Write upsert_partner 取引先マスタ auto-creation in freee. Fuzzy match against existing partners; if new, create. Returns partner_id.

READ 9 tools

Read check_duplicate Check if a transaction already exists in freee (= by date + amount + memo prefix). Use BEFORE register to prev Read check_exclusion 7-rule exclusion check for Japanese accounting. Returns excluded:true if transaction should NOT be auto-journa Read classify_transaction Two-stage classifier for Japanese tax accounting. Stage 1: keyword dictionary match (14 categories × ~50 keywo Read freee_doctor Diagnose the freee connection in ONE shot. Checks: (1) where the access token is sourced (FREEE_ACCESS_TOKEN e Read generate_monthly_report Generate a monthly review report. Takes transaction data (from freee API or CSV import), classifies all transa Read list_freee_companies List all companies (事業所) accessible by the configured freee OAuth token. Returns company IDs + names. Used for Read list_freee_deals List transactions (取引) from freee API for the configured company. Useful for sync + classification dogfood. Read recall_memory 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。 Read reconcile_cross_saas Cross-SaaS reconciliation (= freee ↔ MF). Currently freee-only mode (= MF connector pending Phase 1.B). Detect

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Cockpit

How do I prevent bulk modifications through Cockpit? +

The Cockpit server has 3 write tools including correct_classification, import_csv, upsert_partner. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Cockpit.

How many tools does the Cockpit MCP server expose? +

13 tools across 3 categories: Execute, Read, Write. 9 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Cockpit? +

Register the Cockpit MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Cockpit tool call.

Deterministic rules across all 13 Cockpit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON COCKPIT →

Instant setup, no code required.

13 Cockpit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.