@accos/mcp-server
Connects AI agents to ACCOS for OCR on Thai receipts, tax invoices, and withholding tax certificates via MCP.
README
@accos/mcp-server
ACCOS MCP server — Thai accounting OCR via Model Context Protocol.
Connects Claude Desktop, Cursor, Claude Code, n8n, or any MCP-compatible AI agent to ACCOS so the agent can read Thai receipts, tax invoices, and withholding tax certificates without you writing glue code.
Quick start
1. Get an API key + secret
Generate a key pair at accos.app/settings/api-keys.
Both the key (ak_live_…) and the secret (sk_live_…) are required —
every tool call is HMAC-signed.
2. Add to your MCP client
Claude Desktop — edit claude_desktop_config.json:
{
"mcpServers": {
"accos": {
"command": "npx",
"args": ["-y", "@accos/mcp-server"],
"env": {
"ACCOS_API_KEY": "ak_live_xxx",
"ACCOS_API_SECRET": "sk_live_xxx"
}
}
}
}
Cursor — edit ~/.cursor/mcp.json (same shape).
Claude Code — claude mcp add accos -- npx -y @accos/mcp-server,
then set the two env vars in your shell.
Restart your agent — ACCOS tools appear in the tool list.
Tools
| Tool | Cost | Purpose |
|---|---|---|
inspect_file |
free | Pre-flight: page count, MIME, advice |
read_document |
1 token | Extract data from a single-page receipt/invoice |
verify_tax_id |
1 token | Validate a 13-digit Thai tax ID against the RD/DBD registry |
lookup_master |
1 token | Search master data (vendors/customers/products) |
list_my_templates |
free | List custom templates accessible to this key |
estimate_cost |
free | Dry-run the cost of a planned tool call |
get_balance |
free | Current token balance + active batches |
list_tasks |
free | List open Task Tracker tasks you can see |
my_tasks |
free | Open tasks assigned to you |
get_task |
free | One task in full (checklist, comments, activity) |
set_task_status |
free | Move a task to todo / in_progress / review |
Task Tracker tools
list_tasks, my_tasks, and get_task read the ACCOS Task Tracker
module. They require:
- the API key scope
tasks:read(tick "Grant read access to the Task Tracker module" when creating the key), and - the Task Tracker module enabled on the account.
set_task_status additionally requires the scope tasks:write and editor
access to the task's project. It can only move a task between todo,
in_progress, and review — closing or cancelling a task stays a human
action in the web app.
Visibility follows project membership — you only ever see tasks in
projects you own, are a member of, or that are public. This is enforced
server-side, not by company. Tasks are referenced as KEY-N
(e.g. ACCOS-12); pass that ref to get_task for full detail.
Strict 1-page contract
read_document accepts EXACTLY ONE page per call. Multi-page PDFs are
rejected — split them locally first:
# pypdf example
from pypdf import PdfReader, PdfWriter
for i, page in enumerate(PdfReader("input.pdf").pages):
w = PdfWriter()
w.add_page(page)
w.write(f"page_{i}.pdf")
// pdf-lib example
import { PDFDocument } from "pdf-lib";
const src = await PDFDocument.load(await fs.readFile("input.pdf"));
for (let i = 0; i < src.getPageCount(); i++) {
const out = await PDFDocument.create();
const [pg] = await out.copyPages(src, [i]);
out.addPage(pg);
await fs.writeFile(`page_${i}.pdf`, await out.save());
}
Then call read_document once per page (parallel is fine, max 10 concurrent).
Destination is mandatory
Every read_document call MUST declare where the data is going:
ar— sales invoices your company issuedap— purchase invoices your company receivedwht— withholding tax certificates (50 ทวิ)custom— anything else; also passtemplate_share_code
ACCOS never infers this from content. Ask the user if unclear.
Configuration reference
| env var | required | default |
|---|---|---|
ACCOS_API_KEY |
yes | — |
ACCOS_API_SECRET |
yes | — |
ACCOS_BASE_URL |
no | https://accos.app (must be https:// unless localhost) |
ACCOS_TIMEOUT_MS |
no | 60000 |
License
Apache-2.0
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。