bundesregierung-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bundesregierung-mcp Find recent German government press releases about climate policy"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
bundesregierung-mcp 🇩🇪
mcp-name: io.github.mohammad-abbasi-sh/bundesregierung-mcp
Unofficial read-only MCP server for bundesregierung.de — the German federal government's official site — via its listing pages (press releases, articles / Meldungen, speeches & press conferences) and document pages, whose full text is read from the server-rendered reading area. Latest press releases (612 at last check), articles (732) and speeches (567), newest first, keyword search across the whole site, and full document text — some press releases also carry the official English translation inline. No key, no login.
Built by Mohammad Abbasi as part of the "Germany MCP factory" (Sepehr-style pipeline). Not affiliated with the German federal government or the Presse- und Informationsamt der Bundesregierung.
For AI agents
Add to your MCP client config (stdio):
{
"mcpServers": {
"bundesregierung": {
"command": "uvx",
"args": ["bundesregierung-mcp==0.1.0"]
}
}
}Or run locally: python -m bundesregierung_mcp.server (needs mcp<2, httpx).
Related MCP server: Bundestag MCP Server
Tools
Tool | Description |
| Latest press releases (Pressemitteilungen) of the German federal government, newest first — |
| Latest articles / Meldungen, newest first — |
| Latest speeches, press statements and press conferences (Pressekonferenzen und Reden), newest first — mostly full transcripts ("Im Wortlaut") — |
| Search bundesregierung.de by keyword across the whole site (press releases, articles, speeches) — |
| Full text of one document — press release, article or speech/transcript — |
| Reachability probe (ok / blocked / error) — one polite request |
Example output (breg_press_releases, limit 1):
{"section": "pressemitteilungen", "total_results": 612, "page_count": 62, "page": 1, "count": 1,
"items": [
{"title": "Erklärung von Bundeskanzler Friedrich Merz zum Mehrjährigen Finanzrahmen 2028-2034",
"topline": null,
"link": "https://www.bundesregierung.de/breg-de/aktuelles/pressemitteilungen/erklaerung-von-bundeskanzler-friedrich-merz-zum-mehrjaehrigen-finanzrahmen-2028-2034-2462246",
"type": "Pressemitteilung",
"published": "2026-11-21T12:25:00Z",
"description": null}]}Notes:
The server reads the site's listing pages (
/breg-de/aktuelles/{pressemitteilungen,artikel,pressekonferenzen-und-reden}, verified live 2026-11-22). The results are embedded server-side asBPA.initialSearchResultsJsonin the HTML — there is no RSS feed:/breg-de/service/rss-feeds404s and the pages carry no<link rel="alternate">feed.Pagination quirk, verified live: the site's
?page=is 0-based —?page=Nreturns page N+1. Page 1 carries 11 items, later pages 10. Listing tools fetch successive pages until the requestedlimitis met.Document text, honestly: the full text is read from the server-rendered
#rs_reading_area_contentparagraphs (statement: 7 German + 8 English paragraphs incl. heading, 249 / 306 words; speech transcript: 20 paragraphs, 1,113 words; article: 11 paragraphs, 577 words — all sampled live). Article pages mix in an image caption + "Foto:" credit line and trailing related-link lines ("Pressemitteilung des BMDS: ..."); all three are filtered out of the body.English translations: some press releases carry the official English translation inline (
lang="en-GB"spans wrapping whole paragraphs) — it is returned separately asbody_en(has_english_translation: true). Inline foreign words (e.g. "EUDI-Wallet") are also markedlang="en-GB"but are single words, so a segment counts as English only when the en-GB spans cover ≥ 50% of its text.Speech dates, honestly: speech/transcript pages ("Mitschrift Pressekonferenz") carry NO
<time datetime>— their date is read from the header's German date line ("Freitag, 20. November 2026" →2026-11-20). The featured (image) teaser on the article listing likewise carries no<time>— its date falls back to the item'ssortDatefield (site-local time, no offset).Data: bundesregierung.de public listing and document pages — no key, no login, read-only.
Development
python3 -m venv .venv && .venv/bin/pip install "mcp<2" httpx pytest
.venv/bin/pip install -e .
.venv/bin/python -m pytest tests/ -qtests/test_domain.py— offline, parses the three real captured listing pages (press releases, articles, site search) plus three real document pages (a press-release statement with English translation, an article, a speech transcript)tests/test_live.py— cautious live requests against www.bundesregierung.de
Tests: 29/29 green (22 offline + 7 live, 2026-11-22).
License
PolyForm Noncommercial 1.0.0 — free for personal and non-commercial use; commercial use needs a separate license (see LICENSE).
Built by Mohammad Abbasi — Almanibama · mabbasi.ir
Available Tools
6 toolsbreg_articlesA
Latest articles / Meldungen from bundesregierung.de, newest first. limit: 1..50 (default 10); page: 1-based starting page (default 1). Items carry title, topline, link (a per-document URL for breg_get_document), publish time and a short description.
Inputs: page, limit. Returns: result
breg_get_documentA
Full text of one bundesregierung.de document — a press release, article or speech/transcript. url: a www.bundesregierung.de document URL, e.g. from breg_press_releases (/breg-de/aktuelles/pressemitteilungen/...) or a /breg-de/suche/- alias from breg_search (it redirects to the canonical document). Returns title, publish time, kind (press-release / article / speech / document), the German body text and its word count, plus body_en with the official English translation when the site carries one inline (has_english_translation). Speech pages carry no machine-readable publish time — their date is read from the header's German date line when present. Nothing is ever fabricated.
Inputs: url (required). Returns: result
breg_healthA
Check whether the bundesregierung.de press-releases listing is reachable right now.
Returns status ok (HTTP 200), blocked (HTTP 403/429 — bot wall or rate limit) or error, plus the HTTP status and the probed URL. One polite request; it does not fetch any listings.
Inputs: no named parameters. Returns: result
breg_press_releasesA
Latest press releases (Pressemitteilungen) of the German federal government, newest first. limit: 1..50 (default 10); page: 1-based starting page (default 1). Items carry title, topline, link (a per-document URL for breg_get_document), type, publish time and — for press releases — no description (the teasers carry title + date only).
Inputs: page, limit. Returns: result
breg_searchA
Search bundesregierung.de by keyword across the whole site (press releases, articles, speeches). query: free text, e.g. "Klima" or "Bundeshaushalt 2027". limit: 1..50 (default 10); page: 1-based starting page (default 1). Items carry title, topline, link (a /breg-de/suche/ alias URL — breg_get_document follows it to the canonical document), publish time and a short description.
Inputs: query (required), page, limit. Returns: result
breg_speechesA
Latest speeches, press statements and press conferences (Pressekonferenzen und Reden) of the German federal government, newest first — mostly full transcripts ("Im Wortlaut"). limit: 1..50 (default 10); page: 1-based starting page (default 1). Items carry title, topline, link (a per-document URL for breg_get_document), type and publish time.
Inputs: page, limit. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool maps to a distinct content type or action: three listing endpoints split by content kind (press releases, articles, speeches), a cross-site search, a document fetcher, and a reachability probe. The closest pair is breg_press_releases vs breg_articles, but the descriptions clarify the difference (teasers vs. articles with description text) and the returned `type` field disambiguates further.
All names share a consistent `breg_` prefix and are snake_case, so the family is immediately recognizable. Minor deviation: the listing tools are bare plural nouns (breg_press_releases, breg_articles, breg_speeches) while the others use verb style (breg_search, breg_get_document, breg_health), but the pattern remains readable and predictable.
Six tools is well-scoped for a read-only news/press site integration: three content listings, one search, one document fetch, and one health check. No tool is redundant and nothing feels missing from the surface that would require another endpoint.
The read-only lifecycle is complete: list per content type, search across all types, and fetch full text (with English translation) via a shared document URL. Gaps are minor — no date-range or category filtering on listings/search and no archive-browsing tool, but agents can work around these by paging and searching.
Maintenance
Related MCP Connectors
Search and read government press releases from the US, Korea, UK, EU, New Zealand and Australia.
Search public procurement notices from 17 sources across Germany, the EU and the UK. Read-only.
Read-only search across current job listings on stellenonline.de (German job portal).
Read-only council records from Germany's Ruhr area plus German parliamentary papers.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides access to the official German Federal Legal Information Portal (rechtsinformationen.bund.de) enabling AI agents to search German federal laws, court decisions, and legal documentation with authoritative citations from official sources.524MIT
- AlicenseNot gradedqualityDmaintenanceProvides programmatic access to official German Bundestag parliamentary data, enabling LLMs to answer questions about legislation, voting records, and members.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search and read government press releases from six markets as IPTC ninjs 2.1, including full article retrieval with attribution and quota-aware access.MIT
- AlicenseAqualityBmaintenanceEnables read-only access to German news headlines, section and regional feeds, latest videos, keyword search, and full article text via official RSS feeds. No API key or login is required.7PolyForm Noncommercial 1.0.0