能力标签
MCP服务器
🔌
MCP工具

MCP服务器

基于 TypeScript · 让 AI 助手直接操作你的系统与工具
英文名:e-arveldaja-mcp
⭐ 18 Stars 🍴 5 Forks 💻 TypeScript 📄 Apache-2.0 🏷 AI 7.5分
7.5AI 综合评分
mcptypescripte-arveldaja
✦ AI Skill Hub 推荐

MCP服务器 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。

📚 深度解析

MCP服务器 是一款基于 MCP(Model Context Protocol)标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源,旨在建立 AI 模型与外部工具之间的标准化通信接口,目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装 MCP服务器,你的 AI 助手将获得额外的工具调用能力,可以用自然语言直接操控该工具的功能,无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置,永久增强"——配置完成后,每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上,MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信,工具的功能以"工具列表"的形式暴露给 AI 模型,AI 可以按需调用。MCP服务器 提供了结构化的工具调用接口,使 AI 模型能够精确地理解和使用每个功能点,显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比,MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON,即可让 AI 获得全新能力。AI Skill Hub 将 MCP服务器 评为 AI 评分 7.5 分,属于同类工具中的优质选择。

📋 工具概览

MCP服务器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。

GitHub Stars
⭐ 18
开发语言
TypeScript
支持平台
Windows / macOS / Linux
维护状态
轻量级项目,按需更新
开源协议
Apache-2.0
AI 综合评分
7.5 分
工具类型
MCP工具
Forks
5

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

MCP服务器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。

📌 核心特色
  • 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
  • 提供结构化工具调用接口,显著降低 AI 集成复杂度
  • 支持 Claude Desktop 和 Claude Code 无缝接入,开箱即用
  • 可与其他 MCP 工具组合叠加,构建完整 AI 工作站
  • 轻量无侵入设计,不影响现有系统架构
🎯 主要使用场景
  • 在 Claude Desktop 对话中直接调用本地工具,实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务,代替繁琐手动操作
  • 将多个 MCP 工具组合使用,构建个人专属 AI 工作站
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/iseppo/e-arveldaja-mcp

# 方式二:手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "mcp---": {
      "command": "npx",
      "args": ["-y", "e-arveldaja-mcp"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
📋 安装步骤说明
  1. 确认已安装 Node.js(v18 或以上版本)
  2. 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
  3. 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
  4. 保存配置文件并重启 Claude 客户端
  5. 重启后,在对话中即可使用本工具
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 安装后在 Claude 对话中直接使用
# 示例:
用户: 请帮我用 MCP服务器 执行以下任务...
Claude: [自动调用 MCP服务器 MCP 工具处理请求]

# 查看可用工具列表
# 在 Claude 中输入:"列出所有可用的 MCP 工具"
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "mcp___": {
      "command": "npx",
      "args": ["-y", "e-arveldaja-mcp"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效
📑 README 深度解析 真实文档 完整度 64/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

e-arveldaja MCP Server

npm

MCP server for the Estonian e-arveldaja (RIK e-Financials) REST API. 121 tools, 15 workflow prompts, 12 resources. Works with any MCP client — Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Cline, and others.

v0.14.2 — safer CAMT re-imports. import_camt053 now preserves CAMT bank-reference and counterparty-account metadata in the writable transaction description when the e-arveldaja API drops the dedicated fields. Long bank references are stored as stable hashes, marker-only prior imports still surface in duplicate review when the exact key does not match, and repeated CAMT imports are less likely to create duplicate PROJECT rows. See the changelog for full details. Guided workflow actions. recommend_workflow suggests the safest accounting flow for a natural-language goal, and key workflow/batch tools return a workflow_action_v1 envelope with recommended_next_action, review questions, and approval previews. accounting_inbox is the preferred merged entry point for workspace triage, continue_accounting_workflow is the preferred merged continuation tool, receipt_batch and process_camt053 are the preferred mode-based import/batch entry points, and bank work has reconcile_bank_transactions plus classify_bank_transactions as mode-based entry points. Older focused tools such as run_accounting_inbox_dry_runs, resolve_accounting_review_item, prepare_accounting_review_action, scan_receipt_folder, process_receipt_batch, parse_camt053, import_camt053, reconcile_transactions, and apply_transaction_classifications remain available as compatibility primitives. See the changelog for full details. v0.10.0 is a major update. Large parts of the codebase have been rewritten — credential management, bank reconciliation, audit logging, and batch workflows all received significant changes. You may need to re-add your API credentials after updating, as the credential storage has moved from reading apikey*.txt directly to .env files. Your existing apikey*.txt files will be detected automatically and the server will offer to import them on first start.
Active development. This package is under active development and has not seen extensive real-world testing yet. If you encounter a bug or unexpected behaviour, please let me know via GitHub Issues or email at indrek.seppo@gmail.com.

Start from one inbox-style overview

"Scan this workspace and tell me what can be done automatically, what needs one decision, and what needs accountant review"

This is the recommended first step for non-accountants. The assistant will use the accounting inbox flow to detect likely CAMT files, Wise CSV exports, and receipt folders, propose safe dry-run steps in the right order, and ask only the smallest missing follow-up questions with recommended defaults first.

Accounting inbox and workflow recommendation responses include a workflow block with done, needs_decision, needs_review, recommended_next_action, available_actions, and approval_previews so clients can continue from one compact next step instead of choosing among all tools manually.

Setup

Usage Examples

Once the MCP server is connected, just talk to your AI assistant in natural language:

3. Optional: define company-specific accounting rules

If your company has stable booking conventions that cannot always be derived from the ledger alone, create an optional local file:

accounting-rules.md

This file is human-editable Markdown, not JSON. It is meant for: - counterparty-specific auto-booking defaults when supplier history is missing - owner-expense VAT deduction defaults or account-specific overrides - annual-report overrides for liability maturity and cash-flow category classification

The server reads this file from the project root by default. You can point to another location with EARVELDAJA_RULES_FILE=/path/to/accounting-rules.md.

Confirmed supplier history still wins over local rules for purchase booking defaults.

<details> <summary>Alternative: environment variables</summary>

export EARVELDAJA_API_KEY_ID=...
export EARVELDAJA_API_PUBLIC_VALUE=...
export EARVELDAJA_API_PASSWORD=...

</details>

<details> <summary>Building from source</summary>

```bash git clone https://github.com/iseppo/e-arveldaja-mcp.git cd e-arveldaja-mcp npm install && npm run build

Getting an API Key

  1. Log in to e-arveldaja
  2. Go to SeadistusedÜldised seadistusedLisa uus juurdepääsuluba (Settings → General settings → Add new access token)
  3. Enter any name for the token
  4. Find your public IP address (e.g. at api.ipify.org) and enter it in the allowed IP field. Multiple IPs can be separated by ;
  5. Save — download the apikey.txt file and place it in the working directory where you run your AI assistant

If you don't have a static IP address, you will need to update the allowed IP in e-arveldaja settings whenever your IP changes.

If requests later start failing with 401 Unauthorized, the most common cause is that your public IP changed and no longer matches the allowed IP list. Check the current public IP yourself in a browser (for example, https://api.ipify.org) and update the whitelist in e-arveldaja if needed.

Never commit the apikey.txt file to git.

For the demo server, set the environment variable EARVELDAJA_SERVER=demo.

2. Add your API credentials

Put the downloaded apikey.txt in the working directory where you run your AI assistant. On the first start, the server detects it and offers to verify and import it into a .env file — either locally (just this folder) or globally (works from any folder).

You can also import manually at any time by asking your AI assistant:

"Import my API key from apikey.txt"

For multiple companies, place multiple files (apikey.txt, apikey-company2.txt, etc.) and use list_connections / switch_connection to switch between them.

Workflows (MCP Prompts)

The server includes 15 built-in workflow prompts that any MCP client can discover and use. These guide the AI through multi-step accounting tasks:

PromptDescription
accounting-inboxStart here: scan a workspace, detect likely inputs, suggest the next safe dry-run steps, and ask only the smallest necessary follow-up questions
resolve-accounting-reviewTurn one accounting review item into a concrete next-step plan with compliance references
prepare-accounting-review-actionPrepare the concrete next action for a resolved review item (delete duplicate, save rule, etc.)
book-invoiceBook a purchase invoice from PDF: extract, validate, resolve supplier, preview, create, upload, confirm
receipt-batchScan receipts and create/upload PROJECT purchase invoices through receipt_batch, then optionally confirm after separate approval
import-camtParse CAMT.053 XML, preview imported bank transactions through process_camt053, then create after approval
import-wisePreview Wise CSV import results, fees, duplicates, and Jar skips before execution
classify-unmatchedGroup unmatched bank transactions, preview suggested booking actions, then apply after approval
reconcile-bankMatch bank transactions through reconcile_bank_transactions, then auto-confirm or review manually
month-end-closeBlockers, missing docs, duplicates, trial balance, P&L, balance sheet
new-supplierCreate supplier with Estonian business registry lookup
company-overviewFinancial dashboard: balance sheet, P&L, receivables, payables
lightyear-bookingBook Lightyear investment trades and distributions from CSV
setup-credentialsVerify and import API credentials from apikey.txt into .env storage
setup-e-arveldajaExplain how to configure API credentials when running in setup mode

Claude Code also has these as slash commands: /accounting-inbox, /resolve-accounting-review, /prepare-accounting-review-action, /book-invoice, /receipt-batch, /import-camt, /import-wise, /classify-unmatched, /reconcile-bank, /month-end, /new-supplier, /company-overview, /lightyear-booking, /setup-credentials, /setup-e-arveldaja.

🎯 aiskill88 AI 点评 A 级 2026-05-31

高质量的开源MCP服务器,支持爱沙尼亚e-arveldaja API

📚 实用指南(长尾问题)
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
部署方案
  • 云端托管:可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
e-arveldaja-mcp 中文教程e-arveldaja-mcp 安装报错怎么办e-arveldaja-mcp MCP 配置e-arveldaja-mcp 与同类工具对比e-arveldaja-mcp 最佳实践e-arveldaja-mcp 适合谁用

⚡ 核心功能

👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
⚠️ 常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效

👥 适合人群

Claude Desktop / Claude Code 用户AI 工具开发者需要扩展 AI 能力的专业人士自动化工程师

🎯 使用场景

  • 在 Claude Desktop 对话中直接调用本地工具,实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务,代替繁琐手动操作
  • 将多个 MCP 工具组合使用,构建个人专属 AI 工作站

⚖️ 优点与不足

✅ 优点
  • +Apache-2.0 协议,可免费商用
  • +标准化 MCP 协议,生态互联性强
  • +与 Claude 官方生态无缝对接
  • +即插即用,配置简单快捷
⚠️ 不足
  • 依赖 Claude 客户端,非 Claude 用户无法使用
  • MCP 协议仍在持续演进,接口可能变更
  • 需要一定的配置步骤
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。

📄 License 说明

✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。

🔗 相关工具推荐

📚 相关教程推荐
📰 相关 AI 新闻
🍿 AI 圈相关吃瓜
🗺️ 相关解决方案
🧩 你可能还需要
基于当前 Skill 的能力图谱,自动补全的工具组合

❓ 常见问题 FAQ

e-arveldaja-mcp 是一款TypeScript开发的AI辅助工具。开源MCP工具:Experimental MCP server for Estonian e-arveldaja (RIK e-Financials) API. Not aff。⭐18 · TypeScript 主要应用场景包括:爱沙尼亚电子财务API服务。
💡 AI Skill Hub 点评

经综合评估,MCP服务器 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ Apache-2.0 协议 · 可免费商用 · 直接从 aiskill88 服务器下载,无需跳转 GitHub

📚 深入学习 MCP服务器
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
原始名称 e-arveldaja-mcp
原始描述 开源MCP工具:Experimental MCP server for Estonian e-arveldaja (RIK e-Financials) API. Not aff。⭐18 · TypeScript
Topics mcptypescripte-arveldaja
GitHub https://github.com/iseppo/e-arveldaja-mcp
License Apache-2.0
语言 TypeScript
🔗 原始来源
🐙 GitHub 仓库  https://github.com/iseppo/e-arveldaja-mcp

收录时间:2026-05-31 · 更新时间:2026-06-01 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。