Server data from the Official MCP Registry
Czech invoicing for freelancers and SMEs: invoices, customers, expenses, payments, cash flow.
About
Czech invoicing for freelancers and SMEs: invoices, customers, expenses, payments, cash flow.
Remote endpoints: streamable-http: https://doklad.ai/mcp
Security Report
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
Endpoint verified · Requires authentication · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Found in Source Code
Found by scanning the linked source code. This listing connects to a hosted endpoint, so none of this runs on your machine: it describes what the server software does where it is hosted.
How to Connect
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"ai-doklad-mcp": {
"url": "https://doklad.ai/mcp"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
Doklad.ai MCP Server
Connect AI assistants to Doklad.ai, Czech invoicing software for freelancers (OSVČ) and small companies. The hosted Doklad.ai MCP server lets Claude, ChatGPT, Codex, Claude Code, Cursor, VS Code, Gemini CLI and other Model Context Protocol clients create and send invoices, manage customers, log expenses, record received payments and summarise cash flow in your Doklad.ai account.
| Endpoint | https://doklad.ai/mcp |
| Transport | Streamable HTTP |
| Authentication | OAuth 2.1 (sign in with your Doklad.ai account; PKCE, dynamic client registration) or an API key Authorization: Bearer dk_… |
| Price | Doklad.ai is currently free, MCP included |
| Rate limit | 60 requests per minute per company |
| Official MCP Registry | ai.doklad/mcp |
| Setup guide (Czech) | https://doklad.ai/mcp-fakturace |
This repository holds documentation and client configuration only. The MCP server is hosted and operated by Doklad.ai, so there is nothing to install or run on your side.
Who it is for
- Freelancers (OSVČ) and small Czech companies that invoice in Doklad.ai and want to work with invoices from their AI assistant.
- Accountants and back-office teams automating routine invoicing and payment follow-up.
- Developers building agents on top of Czech invoicing data.
What you can ask
- "Which invoices are overdue and how much is outstanding in total?"
- "Create an invoice for Alfa s.r.o. for 12 hours of consulting at 1,500 CZK excl. VAT, due in 14 days."
- "Email invoice 2026-0142 to the customer."
- "Record a payment of 18,150 CZK received today for invoice 2026-0137."
- "Show revenue, expenses and profit for September."
Connect your client
Every client uses the same URL, https://doklad.ai/mcp. On first use the client opens Doklad.ai in your browser: sign in, pick the company and allow access. No key is copied anywhere. Only the owner or an admin of a company can grant access.
Claude (claude.ai, Claude Desktop, mobile)
Add the connector, or open Customize → Connectors → Add custom connector, enter https://doklad.ai/mcp and sign in. The connector then works on the web, in Claude Desktop and in the mobile app. Free plans allow one custom connector; on Team and Enterprise an Owner adds it under Organization settings → Connectors.
ChatGPT
Turn on Settings → Security and login → Developer mode, then open chatgpt.com/plugins, click +, enter https://doklad.ai/mcp with OAuth authentication and sign in. Developer mode is available on Plus, Pro, Business, Enterprise and Edu.
Claude Code
claude mcp add --transport http --scope user doklad https://doklad.ai/mcp
Then run /mcp, select doklad and choose Authenticate.
Codex (CLI, IDE extension, ChatGPT desktop app)
codex mcp add doklad --url https://doklad.ai/mcp
codex mcp login doklad
Cursor
Install in Cursor, or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"doklad": { "url": "https://doklad.ai/mcp" }
}
}
VS Code (GitHub Copilot agent mode)
Add to .vscode/mcp.json (VS Code 1.99+):
{
"servers": {
"doklad": { "type": "http", "url": "https://doklad.ai/mcp" }
}
}
Gemini CLI
gemini mcp add --scope user --transport http doklad https://doklad.ai/mcp
Then run /mcp auth doklad. This repository is also a Gemini CLI extension (gemini-extension.json).
API key (n8n, scripts, clients without OAuth)
Create a key in Doklad.ai under Integrace → API klíče a webhooky → MCP server and send it as Authorization: Bearer dk_…:
claude mcp add --transport http doklad https://doklad.ai/mcp --header "Authorization: Bearer $DOKLAD_API_KEY"
# ~/.codex/config.toml
[mcp_servers.doklad]
url = "https://doklad.ai/mcp"
bearer_token_env_var = "DOKLAD_API_KEY"
Claude Desktop's claude_desktop_config.json only runs local servers, so use the mcp-remote bridge (Node.js 20.18+):
{
"mcpServers": {
"doklad": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://doklad.ai/mcp", "--header", "Authorization:${DOKLAD_AUTH_HEADER}"],
"env": { "DOKLAD_AUTH_HEADER": "Bearer dk_YOUR_KEY" }
}
}
}
Tools
| Tool | What it does | Access |
|---|---|---|
list_invoices | List invoices, filtered by status, customer, text search or date range | Read |
get_invoice | One invoice with line items and customer details | Read |
create_invoice | Create an invoice: customer, line items (description, quantity, unit price, VAT rate) and due date | Write |
update_invoice | Update an invoice; only the fields you pass change | Write |
delete_invoice | Delete an invoice (drafts and cancelled invoices only) | Destructive |
send_invoice_email | Email an invoice to the customer | Write, sends email |
get_invoice_pdf_url | Download URL of an invoice PDF | Read |
record_payment | Record a received payment against an invoice (bookkeeping entry, moves no money) | Write |
list_customers | Search customers by name, IČO or email | Read |
get_customer | One customer | Read |
create_customer | Create a customer | Write |
update_customer | Update a customer | Write |
list_expenses | List expenses, optionally by status | Read |
get_expense | One expense | Read |
create_expense | Record an expense | Write |
get_invoice_stats | Invoice counts: total, paid, sent, overdue, drafts | Read |
get_cash_flow_summary | Revenue, expenses and profit for a period | Read |
Every tool carries MCP annotations (title, readOnlyHint, destructiveHint, openWorldHint), so clients ask for confirmation before tools that change data or send email.
Security
- OAuth 2.1 with PKCE (S256), dynamic client registration (RFC 7591), refresh-token rotation with reuse detection, RFC 9207
iss. Discovery:https://doklad.ai/.well-known/oauth-protected-resource/mcp. - Access is granted per company on a Doklad.ai consent page; only owners and admins can grant it. Connections are listed and revocable under Integrace → API klíče a webhooky → Připojené aplikace.
- Every tool call is written to the company's audit log. Tokens and API keys are stored only as hashes.
- 60 requests per minute per company.
Česky
Návod k připojení v češtině: https://doklad.ai/mcp-fakturace (Claude, ChatGPT, Codex, Claude Code, Cursor, VS Code, Gemini CLI, n8n).
Support
podpora@doklad.ai · https://doklad.ai
License
The documentation and configuration files in this repository are MIT licensed. The Doklad.ai service is subject to its terms and privacy policy.
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Fetch
Freeby Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
Worldmonitor
Freeby Koala73 · Developer Tools
Live markets, conflicts, country risk, chokepoints, energy, and China decision signals. 86 tools.
Paperclip
Freeby Paperclipai · Developer Tools
Trending hip-hop artist momentum scores across four cultural dimensions.
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
