cz-eli-mcp
Enables searching and retrieving Czech legal acts from the e-Sbirka database via SPARQL, including metadata and full consolidated text with verifiable citations.
README
cz-eli-mcp
<!-- mcp-name: io.github.matematicsolutions/cz-eli-mcp -->
An MCP server for the Czech e-Sbirka legal database (e-sbirka.gov.cz), the official
Collection of Laws (Sbirka zakonu), via its open-data SPARQL endpoint. It searches acts and
fetches their full consolidated text, with verifiable citations.
Part of the MateMatic eu-legal-mcp production line - after PL, DE, AT, ES, FI, IE, NL, SE, FR,
LU and DK. Same citation contract, e-Sbirka source. This is the first connector in the line that
talks SPARQL/RDF rather than a REST/XML API.
Scope. This MVP searches acts (by year and/or a citation substring), returns metadata, and assembles the full consolidated text of the latest version. ~92,000 acts, updated daily, licensed CC BY 4.0. Language: Czech. Every response carries a
dataset_note.ELI is national, not data.europa.eu. The act IRI follows the ELI URI template (
eli/cz/sb/{year}/{number}) but is minted by the e-Sbirka open-data graph (opendata.eselpoint.gov.cz), not resolvable ondata.europa.eu. The readable page is one-sbirka.gov.cz. Every response carries aneli_notesaying so.Text is assembled, not a single file. e-Sbirka exposes the consolidated text as ordered HTML fragments over SPARQL;
cz_get_textreconstructs the plain text from them. There is no single official XML/PDF manifestation.
The tools
| Tool | What it does |
|---|---|
cz_search |
Find acts by year and/or a citation substring (discovery). |
cz_get_act |
Metadata for an act by year + number, plus the latest consolidated version date. |
cz_get_text |
Full consolidated text of an act, assembled from the latest version's fragments. |
Every response carries the contract: eli_uri (the national ELI IRI, e.g.
https://opendata.eselpoint.gov.cz/esel-esb/eli/cz/sb/2019/110), human_readable_citation
(e.g. 110/2019 Sb.), and source_url (the e-sbirka.gov.cz page).
Install
Run it with no install step (once published to PyPI):
uvx cz-eli-mcp
Or from source:
cd cz-eli-mcp
pip install -e .
Configure (Claude Code / any MCP client)
{
"mcpServers": {
"cz-eli-mcp": { "command": "cz-eli-mcp" }
}
}
Environment:
CZ_ELI_ENDPOINT- defaulthttps://opendata.eselpoint.gov.cz/sparqlCZ_ELI_CACHE_DIR- default~/.matematic/cache/cz-eliCZ_ELI_AUDIT_DIR- default~/.matematic/audit
No API key. The e-Sbirka open-data SPARQL endpoint is keyless.
Governance
- Public data only - read-only SPARQL against e-Sbirka; no client data leaves the machine.
- Audit log - every tool call appends one JSON line to
~/.matematic/audit/cz-eli-mcp.jsonl. - Vendor-neutral - talks only to
opendata.eselpoint.gov.cz; no LLM provider, no telemetry. - Verifiable citations - every response is independently checkable via
source_url.
See CONSTITUTION.md and DISCOVERY.md.
Tests
pip install -e ".[dev]"
pytest tests/test_instructions_drift.py tests/test_parse.py -v # offline
pytest tests/test_smoke.py -v # hits the live SPARQL endpoint
Licence
Apache-2.0. © Matematic Solutions / Wieslaw Mazur. e-Sbirka data is CC BY 4.0 (Czech Ministry of
the Interior); relayed with attribution and a source_url.
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。