mcp-fleet
12 MCP tools: invoice→JSON, text→SQL, PII redaction, regex & more. Free to try, pay per call.
使うべきか
品質と安全性
検出事項（3）
- LOWTool 'json_schema_infer' description lacks action verbjson_schema_infer 内
- LOWTool 'email_draft' description lacks action verbemail_draft 内
- LOWTool 'code_explain' description lacks action verbcode_explain 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"mcp-fleet": {
"url": "https://mcp-fleet.nebula-labs.online/mcp/sse"
}
}
}リモートエンドポイント
https://mcp-fleet.nebula-labs.online/mcp/ssessehttps://mcp-fleet.nebula-labs.online/mcp/sse?src=mcp_registrysseできること
ツール一覧
ツール（12）
⚪invoice_pdf_to_json(invoice_text)
Convert raw invoice text (extracted from PDF, email, or image OCR) into a structured JSON object. Returns vendor, date, line items, totals, and currency in a machine-readable format.
入力スキーマ
{
"type": "object",
"properties": {
"invoice_text": {
"type": "string",
"description": "The raw text content of the invoice. Can be messy — include all text exactly as extracted.",
"minLength": 10
}
},
"required": [
"invoice_text"
]
}⚪text_to_compliance_checklist(requirement_text, context)
Convert a block of requirement, regulation, or specification text into a structured compliance checklist. Each checklist item includes a category, obligation, priority (HIGH/MEDIUM/LOW), and verification method.
入力スキーマ
{
"type": "object",
"properties": {
"requirement_text": {
"type": "string",
"description": "The requirement or specification text to analyze. Can be a contract clause, regulatory text, internal policy, or any document describing obligations.",
"minLength": 20
},
"context": {
"type": "string",
"description": "Optional: additional context about the industry or use case (e.g. 'SaaS company, GDPR jurisdiction, healthcare data'). Helps the model assign more accurate priorities."
}
},
"required": [
"requirement_text"
]
}⚪text_to_sql(request)
Convert a natural-language data question into a SQL query. Returns the SQL, dialect, and tables used.
入力スキーマ
{
"type": "object",
"properties": {
"request": {
"type": "string",
"description": "Natural-language question, optionally with a schema description.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"request"
]
}⚪json_schema_infer(sample_json)
Infer a JSON Schema (draft 2020-12) from a sample JSON document.
入力スキーマ
{
"type": "object",
"properties": {
"sample_json": {
"type": "string",
"description": "A sample JSON document (object or array).",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"sample_json"
]
}⚪regex_builder(description)
Build a regular expression from a plain-language description, with an explanation and test cases.
入力スキーマ
{
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "What the regex should match, in plain language.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"description"
]
}🟢cron_explain(cron_expression)
Explain a cron expression in plain English and list the next run times.
入力スキーマ
{
"type": "object",
"properties": {
"cron_expression": {
"type": "string",
"description": "A standard 5-field cron expression, e.g. '30 9 * * 1-5'.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"cron_expression"
]
}🟢sentiment_analyze(text)
Analyze sentiment of text with an overall score and per-aspect breakdown.
入力スキーマ
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The text to analyze (review, message, feedback).",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"text"
]
}⚪pii_redact(text)
Locally detect and redact high-confidence PII (emails, phones, SSNs, credit cards, IPs) from text — raw data never leaves the server. Returns redacted text and found entities.
入力スキーマ
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text that may contain personal data.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"text"
]
}⚪email_draft(brief)
Turn bullet points or a brief into a polished professional email (subject + body).
入力スキーマ
{
"type": "object",
"properties": {
"brief": {
"type": "string",
"description": "Bullet points or a short brief describing the email to write.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"brief"
]
}⚪meeting_summarize(transcript)
Summarize a meeting transcript into a summary, action items, decisions, and participants.
入力スキーマ
{
"type": "object",
"properties": {
"transcript": {
"type": "string",
"description": "The raw meeting transcript or notes.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"transcript"
]
}🟢code_explain(code)
Explain what a code snippet does, step by step, with complexity and risk notes.
入力スキーマ
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The source code to explain.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"code"
]
}⚪unit_test_outline(code)
Generate a unit-test outline (cases + coverage targets) for a function.
入力スキーマ
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The function or module to generate test cases for.",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"code"
]
}コミュニティ
エビデンス