e-conomic MCP Server
Enables natural language management of e-conomic accounting, including customers, products, and invoices, with full CRUD and PDF download capabilities.
README
e-conomic-mcp-server
Perfect for anyone who, like me, is more geek than bookkeeper. Finally there is a bit of fun in bookkeeping. Who would have thought.
Getting started
Install dependencies:
npm install
Run the server:
npm start
Environment variables
The server reads e-conomic credentials from the environment:
ECONOMIC_APP_SECRET_TOKEN(required)ECONOMIC_AGREEMENT_GRANT_TOKEN(required)ECONOMIC_BASE_URL(optional, defaults tohttps://restapi.e-conomic.com)ECONOMIC_DEBUG(optional, set totrueto emit JSON debug logs to stderr)
You'll find all the information on both tokens you need to get started here. It's a bit complex but not as boring and annoying as it looks like by first glimpse. Pinky promise!
Recommended ways to supply tokens
- Local development: keep secrets in
.envand runnpm startfrom the repo root sodotenvloads them. - Desktop MCP clients: either start the server from a shell that has
.envloaded, or pass env variables in the client config if you want the client to spawn the server for you. - CI/shared environments: use your secret manager (GitHub Actions secrets, etc.) and inject env vars at runtime. Do not commit
.env.
Tools
Tool list:
- Connectivity:
hello - Customers:
list_customers,get_customer,update_customer - Products:
list_products,upsert_product - Draft invoices:
list_invoice_drafts,get_invoice_draft,create_invoice_draft,update_invoice_draft,book_invoice_draft - Booked invoices:
list_booked_invoices,get_booked_invoice,download_invoice_pdf - Reference data:
list_payment_terms,list_customer_groups,list_vat_zones
Tool reference
| Category | Tool | Purpose | Arguments | Returns / Notes |
|---|---|---|---|---|
| Connectivity | hello |
Sanity check to confirm the server is reachable. | { "name": "YourName" } |
Greeting text. |
| Customers | list_customers |
List customers with pagination. | { "pageSize": number, "page": number } |
Paginated customer collection. |
| Customers | get_customer |
Fetch one customer by customer number. | { "customerNumber": number } |
Customer details. |
| Customers | update_customer |
Update customer fields. | { "customerNumber": number, ...fields } |
Updated customer object. |
| Products | list_products |
List products with pagination. | { "pageSize": number, "page": number } |
Paginated product collection. |
| Products | upsert_product |
Create or update a product. | { "productNumber": string, "name": string, "salesPrice": number, "productGroupNumber": number, ...optionalFields } |
Product object. productGroupNumber is required on create. |
| Draft invoices | list_invoice_drafts |
List draft invoices with pagination. | { "pageSize": number, "page": number } |
Paginated draft collection. |
| Draft invoices | get_invoice_draft |
Fetch a draft invoice. | { "draftInvoiceNumber": number } |
Draft invoice details. |
| Draft invoices | create_invoice_draft |
Create a new draft invoice. | { "customerNumber": number, "currency": "DKK", "date": "YYYY-MM-DD", "lines": [...], "createCustomerIfMissing": boolean, "newCustomer": {...} } |
Created draft. If a line omits productNumber, it defaults to "1". If createCustomerIfMissing is true and the customer does not exist, a new customer is created from newCustomer. |
| Draft invoices | update_invoice_draft |
Update a draft invoice. | { "draftInvoiceNumber": number, ...fields } |
Updated draft invoice. |
| Draft invoices | book_invoice_draft |
Book a draft into a booked invoice. | { "draftInvoiceNumber": number } |
Booked invoice payload. |
| Booked invoices | list_booked_invoices |
List booked invoices with pagination. | { "pageSize": number, "page": number } |
Paginated booked invoice collection. |
| Booked invoices | get_booked_invoice |
Fetch a booked invoice. | { "bookedInvoiceNumber": number } |
Booked invoice details. |
| Booked invoices | download_invoice_pdf |
Download a booked invoice PDF. | { "bookedInvoiceNumber": number } |
{ "base64": "..." }. |
| Reference data | list_payment_terms |
List payment terms. | { "pageSize": number, "page": number } |
Payment terms collection. |
| Reference data | list_customer_groups |
List customer groups. | { "pageSize": number, "page": number } |
Customer groups collection. |
| Reference data | list_vat_zones |
List VAT zones. | { "pageSize": number, "page": number } |
VAT zones collection. |
MCP client setup
Claude Desktop
Add an MCP server entry to your Claude Desktop config file and restart Claude Desktop:
{
"mcpServers": {
"e-conomic": {
"command": "node",
"args": ["/absolute/path/to/e-conomic-mcp-server/src/server.js"],
"env": {
"ECONOMIC_APP_SECRET_TOKEN": "your_token",
"ECONOMIC_AGREEMENT_GRANT_TOKEN": "your_token",
"ECONOMIC_BASE_URL": "https://restapi.e-conomic.com"
}
}
}
}
Common config locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\\Claude\\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Claude Code
Add the MCP server via Claude Code:
claude mcp add-json e-conomic '{
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/e-conomic-mcp-server/src/server.js"],
"env": {
"ECONOMIC_APP_SECRET_TOKEN": "...",
"ECONOMIC_AGREEMENT_GRANT_TOKEN": "...",
"ECONOMIC_BASE_URL": "https://restapi.e-conomic.com"
}
}'
Use --scope project to write a shared .mcp.json file in the repo, or --scope user to make it global for your user.
Codex CLI (OpenAI)
Add the MCP server using Codex CLI:
codex mcp add e-conomic --env ECONOMIC_APP_SECRET_TOKEN=... \
--env ECONOMIC_AGREEMENT_GRANT_TOKEN=... \
--env ECONOMIC_BASE_URL=https://restapi.e-conomic.com \
-- node /absolute/path/to/e-conomic-mcp-server/src/server.js
Codex stores MCP configuration in ~/.codex/config.toml if you prefer to edit it directly.
Gemini CLI
Add to your Gemini CLI settings (user or project settings):
{
"mcpServers": {
"e-conomic": {
"command": "node",
"args": ["/absolute/path/to/e-conomic-mcp-server/src/server.js"],
"env": {
"ECONOMIC_APP_SECRET_TOKEN": "your_token",
"ECONOMIC_AGREEMENT_GRANT_TOKEN": "your_token",
"ECONOMIC_BASE_URL": "https://restapi.e-conomic.com"
}
}
}
}
Settings files are located at ~/.gemini/settings.json (user) or <project>/.gemini/settings.json (project). System-wide settings live under /etc/gemini-cli/settings.json (Linux), C:\\ProgramData\\gemini-cli\\settings.json (Windows), or /Library/Application Support/GeminiCli/settings.json (macOS).
License
MIT License. See LICENSE for details.
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.