lobbywatch-mcp
An MCP server that connects AI models to the Lobbywatch.ch database, providing access to Swiss parliamentarians' conflicts of interest, lobby groups, access badges, and transparency scores.
README
ποΈ lobbywatch-mcp
An MCP server that connects AI models to Lobbywatch.ch, the largest lobby database of the Swiss Federal Parliament β conflicts of interest, lobby groups, access badges, and transparency scores.
Part of the Swiss Public Data MCP Portfolio β connecting AI models to Swiss public data sources.
π― Anchor Demo Query
"Welche Mitglieder der WBK-N haben Interessenbindungen zu Bildungsverlagen oder privaten BildungstrΓ€gern, und wie ist ihre Transparenz-Bewertung?"
Which members of the National Council's Education Commission have declared conflicts of interest with educational publishers or private education providers, and how does their compensation transparency score compare?
β More use cases by audience β
Overview
Lobbywatch.ch maintains the largest public database on Swiss federal parliamentarians and their connections to lobby organisations: 245 parliamentarians, ~7'800 interessenbindungen (declared mandates), 139 lobby groups, 368 access-badge holders, updated weekly, licensed CC BY-SA 4.0.
lobbywatch-mcp exposes this data to Large Language Models via the Model Context Protocol. It is designed to be used alongside parlament-mcp (the official Swiss Parliament's Curia Vista data): the pair makes it possible to ask what a parliamentarian did officially and who they are connected to β in a single conversation.
Features
- Dump-first, API-fallback architecture. The weekly JSON dump is the primary source (stable, verified in production); the live
dataIFREST API is used only where it returns reliable data (lobby groups, search). - Seven Phase 1 tools β parliamentarian lookup, conflict-of-interest listing, branche search, lobby group fetch, rankings, transparency quota, cache control.
- CC BY-SA 4.0 attribution baked into every response via Pydantic envelopes.
- Dual transport β
stdiofor Claude Desktop,streamable-http/ssefor cloud deployments. - Fuzzy name matching via rapidfuzz for natural LLM input like "Jositsch" or "Wehrli".
- No authentication required (Phase 1 β No-Auth-First).
Architecture
βββββββββββββββββββββββββββββββ
LLM client β LobbywatchClient β
(Claude Desktop, β β
Inspector, β¦) β βββββββββββββββββββββ β
β β β Dump cache β β cms.lobbywatch.ch
β MCP β β (24 h TTL, β β ββββββββββββββββββββ
βΌ stdio / β β ~80 MB resident)βββββββΌββββββΊβ weekly JSON β
βββββββββββ HTTP β βββββββββββββββββββββ β β export (~17 MB) β
β FastMCP βββββββΊβ β ββββββββββββββββββββ
β server β β βββββββββββββββββββββ β ββββββββββββββββββββ
βββββββββββ β β dataIF REST βββββββΌββββββΊβ /interface/v1/ β
β β (live fallback) β β β json/β¦ β
β βββββββββββββββββββββ β ββββββββββββββββββββ
βββββββββββββββββββββββββββββββ
Outbound HTTP runs through a single httpx.AsyncClient with follow_redirects=False, an SSRF guard that blocks RFC1918 / link-local / metadata IPs, and an httpx event hook that re-resolves on every request. The dump path is the primary source of truth for parliamentarian queries; dataIF is only used for lobby group lookups and the search endpoint.
Prerequisites
- Python 3.11 or newer
- Internet access to download the weekly Lobbywatch JSON export (~17 MB zipped)
Installation
From PyPI (after first release):
pip install lobbywatch-mcp
From source:
git clone https://github.com/malkreide/lobbywatch-mcp.git
cd lobbywatch-mcp
pip install -e ".[dev]"
Usage
Standalone
lobbywatch-mcp
This starts the server in stdio mode. For HTTP:
LOBBYWATCH_MCP_TRANSPORT=http LOBBYWATCH_MCP_PORT=8000 lobbywatch-mcp
Container
A hardened multi-stage Dockerfile ships with the repo (non-root,
read-only-rootfs compatible). See docs/deployment.md
and deploy/docker-compose.example.yml
for resource limits, sticky-LB guidance and egress hardening.
docker build -t lobbywatch-mcp:0.2.0 .
docker run --rm -p 127.0.0.1:8000:8000 lobbywatch-mcp:0.2.0
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"lobbywatch": {
"command": "uvx",
"args": ["lobbywatch-mcp"]
}
}
}
A full example is provided in claude_desktop_config.json.
Example Queries
Once connected, try prompts such as:
- "Give me the top 10 parliamentarians by number of interessenbindungen in the SP party."
- "Which WBK-N members have mandates in the publishing or education industry?"
- "Look up the lobby group 'economiesuisse' and list its connected parliamentarians."
- "What is the compensation-transparency score distribution for the finance commission (FK-N)?"
Tools
All tool names use the lobbywatch_ namespace prefix (since 0.2.0) to
avoid collisions with sibling portfolio servers.
| Tool | Purpose | Source |
|---|---|---|
lobbywatch_get_parlamentarier(name_or_id) |
Full profile + all conflicts of interest | Dump |
lobbywatch_list_interessenbindungen(name_or_id, nur_hauptberuflich, nur_aktiv) |
Filtered mandate list | Dump |
lobbywatch_search_parlamentarier_nach_branche(branche_query, kommission, limit) |
Cross-filter by industry and commission | Dump |
lobbywatch_get_lobbygruppe(name_or_id) |
Lobby group with connected MPs and organisations | Live dataIF |
lobbywatch_get_ranking(kriterium, kommission, partei, limit) |
Top-N by criterion | Dump |
lobbywatch_get_transparenzquote(kommission) |
Distribution of compensation transparency labels | Dump |
lobbywatch_refresh_dump() / lobbywatch_dump_status() |
Cache control | Dump |
Configuration
All behaviour is controlled via environment variables:
| Variable | Default | Purpose |
|---|---|---|
LOBBYWATCH_MCP_TRANSPORT |
stdio |
Transport (stdio, http, sse) |
LOBBYWATCH_MCP_HOST |
127.0.0.1 |
HTTP bind host (set to 0.0.0.0 only behind an auth gateway) |
LOBBYWATCH_MCP_PORT |
8000 |
HTTP bind port |
LOBBYWATCH_MCP_CACHE_DIR |
~/.cache/lobbywatch-mcp |
Dump cache location |
LOBBYWATCH_MCP_CACHE_TTL |
86400 (24h) |
Cache time-to-live in seconds |
LOBBYWATCH_MCP_HTTP_TIMEOUT |
60 |
HTTP timeout in seconds |
LOBBYWATCH_MCP_CORS_ORIGINS |
(unset) | Comma-separated origin allow-list for HTTP/SSE; when set, exposes Mcp-Session-Id to browsers |
LOBBYWATCH_MCP_LOG_FORMAT |
text |
text (stdlib formatter) or json (structured via structlog) |
LOBBYWATCH_MCP_LOG_LEVEL |
INFO |
DEBUG / INFO / WARNING / ERROR |
LOBBYWATCH_MCP_OTEL_ENABLED |
0 |
Set to 1 to enable OpenTelemetry tracing (requires pip install 'lobbywatch-mcp[obs]') |
LOBBYWATCH_MCP_OTEL_ENDPOINT |
(unset) | OTLP/HTTP collector endpoint (e.g. http://localhost:4318/v1/traces) |
Project Structure
lobbywatch-mcp/
βββ src/lobbywatch_mcp/
β βββ __init__.py
β βββ __main__.py # CLI + transport selection
β βββ config.py # URLs, cache paths, attribution
β βββ client.py # Dump download + dataIF client
β βββ models.py # Pydantic v2 response envelopes
β βββ server.py # FastMCP tool registrations
βββ tests/
β βββ conftest.py # Fixture parliamentarians
β βββ test_client.py # Respx-mocked unit tests
β βββ test_server.py # Tool integration tests
β βββ test_live.py # @pytest.mark.live β excluded from CI
βββ .github/workflows/
β βββ ci.yml # Test matrix + ruff
β βββ publish.yml # PyPI OIDC Trusted Publisher
βββ claude_desktop_config.json
βββ pyproject.toml
βββ ...
Data License & Attribution
The code is released under the MIT License.
The data served through this MCP is Β© Lobbywatch.ch and licensed under CC BY-SA 4.0. Every response envelope includes the attribution string. Downstream users must:
- Credit Lobbywatch.ch as the data source.
- Share derivative datasets under the same CC BY-SA 4.0 terms.
- Understand that Lobbywatch is a community-researched database β not an official register. It is authoritative for transparency research but should not be confused with the Federal Parliament's own declarations.
Known Limitations
- The upstream
/table/parlamentarier/...dataIFREST endpoint currently returns empty result sets. The server works around this by using the weekly JSON dump instead. zutrittsberechtigungen(access badges) are not populated in the "essential" dump variant used here. A future release will add a dedicated tool using the non-essential dump.
Contributing
See CONTRIBUTING.md.
Changelog
See CHANGELOG.md.
License
MIT License β see LICENSE. Data CC BY-SA 4.0 β see LICENSE Β§ Data notice.
Author
malkreide Β· GitHub
Part of the Swiss Public Data MCP Portfolio.
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.