Legal Text Mcp De
by klein-businesscommunityv2.1.3
An MCP server for accessing German legal texts, including federal, state, and EU laws, with provenance metadata. It exposes the corpus through MCP tools, read-only legal:// resources, and an HTTP API, using official sources like gesetze-im-internet.de and EUR-Lex.
From the registry: German federal & state legal texts (BGB, DSGVO, …) with canonical IDs and cite-grade provenance.
Install & configure
Prerequisites
- optionalInstall uvInstall the uv Python package manager/runtime to run the recommended uvx-based server command.
https://docs.astral.sh/uv/$ <install uv via your system package manager or official installer> - optionalOptional: install Python package directlyIf not using uvx, you can install the package from PyPI with pip.
https://pypi.org/project/legal-text-mcp-de/$ pip install legal-text-mcp-de==2.1.3 - requiredCorpus data bundleProvide legal text corpus data. With the recommended uvx path, the server auto-downloads the latest signed corpus bundle from GHCR on first run. Alternative modes may require setting DATASET_PATH to a trusted .tar.zst corpus bundle.https://github.com/klein-business/legal-text-mcp-de/pkgs/container/legal-text-mcp-de
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `legal-text-mcp-de` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Corpus data bundle** — Provide legal text corpus data. With the recommended uvx path, the server auto-downloads the latest signed corpus bundle from GHCR on first run. Alternative modes may require setting DATASET_PATH to a trusted .tar.zst corpus bundle. (https://github.com/klein-business/legal-text-mcp-de/pkgs/container/legal-text-mcp-de)
Optional prerequisites:
- Install uv — Install the uv Python package manager/runtime to run the recommended uvx-based server command. Run: `<install uv via your system package manager or official installer>` (https://docs.astral.sh/uv/)
- Optional: install Python package directly — If not using uvx, you can install the package from PyPI with pip. Run: `pip install legal-text-mcp-de==2.1.3` (https://pypi.org/project/legal-text-mcp-de/)
Canonical MCP server config (HTTP transport):
- url: `http://localhost:8001/mcp`
Note: Recommended install path is `uvx legal-text-mcp-de serve`. The README states the default transport is streamable HTTP at `http://localhost:8001/mcp`. A public hosted service is also documented at `https://mcp.klein.business/legal/de`, but the local uvx path is the simplest portable default. For pip-installed or self-built corpus modes, `DATASET_PATH=<your-corpus-path>` may be needed; with the recommended uvx path it is not required because the corpus auto-downloads on first run.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Recommended install path is `uvx legal-text-mcp-de serve`. The README states the default transport is streamable HTTP at `http://localhost:8001/mcp`. A public hosted service is also documented at `https://mcp.klein.business/legal/de`, but the local uvx path is the simplest portable default. For pip-installed or self-built corpus modes, `DATASET_PATH=<your-corpus-path>` may be needed; with the recommended uvx path it is not required because the corpus auto-downloads on first run.
Tools (10)
list_laws
List loaded laws with optional metadata filtering.
get_law
Return law metadata and normalized norm summaries.
get_norm
Return one structured norm.
search_laws
Search normalized law texts.
resolve_citation
Resolve structured legal citations without legal interpretation.
get_source_metadata
Get source metadata for a code or corpus scope.
get_source_limitations
Get limitations of the source corpus.
get_corpus_coverage
Get corpus coverage information.
get_related_norms
Get norms related to a given law and norm.
research_topic
Run multi-step legal research over the corpus with candidate search, ranking, related-norm loading, and synthesis.
Environment variables
DATASET_PATHrequiredPath to the legal text corpus bundle or fixture corpus used by the server.Prerequisites
- • Python 3.12
Packages
legal-text-mcp-de
pypiv2.1.3transport: stdio
ghcr.io/klein-business/legal-text-mcp-de:2.1.3
ocitransport: stdio
Details
- Language
- Python
- License
- Apache-2.0
- Released
- May 18, 2026
- Last commit
- Jun 29, 2026
- Registry name
- io.github.klein-business/legal-text-mcp-de