@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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.