mcp-server-datovka
An MCP server exposing the Czech ISDS Data Box system (Datové schránky) as tools, built on fastmcp and python3-datovka.
README
mcp-server-datovka
An MCP server exposing the Czech ISDS Data Box system ("Datové schránky") as tools, built on fastmcp and python3-datovka.
Tools
| Tool | Description |
|---|---|
list_received_messages(limit=20) |
Summaries of received messages, most recent first |
list_sent_messages(limit=20) |
Summaries of sent messages, most recent first |
get_message(message_id, include_attachment_content=False) |
Full message with documents; attachment bytes are base64-encoded and only included on request |
mark_message_read(message_id) |
Mark a received message as read |
send_message(recipient_box_id, subject, attachments, ...) |
Send a new message; attachments is a list of {filename, mime_type, content_base64, is_main} dicts, exactly one of which must be is_main=True |
send_text_message(recipient_box_id, subject, body) |
Compose plain text as a PDF and send it as the message's main document — no existing file needed |
find_data_box(query, limit=10) |
Look up a recipient's data box ID by name, trade name, or IČO. Uses the offline seznamds directory first (fast, unlimited), falling back to the live, rate-limited ISDS search API if it's absent or finds nothing. The response includes source and data_age_days so a stale offline snapshot doesn't get presented as current. |
ping() |
Verify the session is alive |
Messages in ISDS are envelope + document attachments, not a body text field
— that's why sending "just text" (send_text_message) means rendering it
to a PDF first, using the system's DejaVu Sans font so Czech diacritics
render correctly.
Configuration
Credentials are read once from the environment at startup and are never tool parameters, so the LLM driving the server can't see or choose them:
export DATOVKA_URL="https://ws1.mojedatovaschranka.cz/" # optional, this is the default; trailing slash required
export DATOVKA_USERNAME="..."
export DATOVKA_PASSWORD="..."
Install the optional seznamds package for fast, unlimited recipient
lookups via find_data_box:
apt install seznamds
Without it, find_data_box still works but falls back to the live,
rate-limited ISDS search API for every lookup.
Running
mcp-server-datovka
Or point an MCP client at it directly:
python -m mcp_server_datovka.server
Requirements
libdatovka8+python3-datovka(orpip install datovka)fastmcppython3-fpdf(fpdf2) +fonts-dejavu-core, forsend_text_messageseznamds(recommended, optional), for fast offlinefind_data_boxlookups
License
LGPL-3.0-or-later.
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.