Gruenerator Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Gruenerator Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Model Context Protocol (MCP) server that gives AI assistants direct access to Green Party political programs from Germany and Austria.
<!-- Add screenshot or GIF of MCP client using Gruenerator --> Coming soon: Demo of search functionality in action
| Collection | Description | Filters |
|---|---|---|
oesterreich | Die Grünen Austria: EU Election, Basic Program, National Council | title |
deutschland | Bündnis 90/Die Grünen: Basic Program, EU Election, Government Program | title |
bundestagsfraktion | Green Parliamentary Group: Positions and expert content | section |
gruene-de | gruene.de website: Positions, topics, and news | section |
gruene-at | gruene.at website: Positions, topics, and news | section |
kommunalwiki | KommunalWiki: Municipal politics knowledge (Heinrich Böll Foundation) | article_type, category |
boell-stiftung | Heinrich-Böll-Stiftung: Analyses, dossiers, and atlases | content_type, topic, region |
Before you begin, ensure you have:
# Build image
docker build -t gruenerator-mcp .
# Run container
docker run -d \
--name gruenerator-mcp \
-p 3000:3000 \
-e QDRANT_URL=https://your-qdrant.com \
-e QDRANT_API_KEY=your-api-key \
-e MISTRAL_API_KEY=your-mistral-key \
gruenerator-mcp# Clone repository
git clone https://github.com/Movm/Gruenerator-MCP.git
cd Gruenerator-MCP
# Install dependencies
npm install
# Set environment variables
cp .env.example .env
# Edit .env with your credentials
# Start server
npm start
# Or with auto-reload
npm run devhttps://github.com/Movm/Gruenerator-MCP| Variable | Description | Required |
|---|---|---|
QDRANT_URL | URL to Qdrant instance | Yes |
QDRANT_API_KEY | API key for Qdrant | Yes |
MISTRAL_API_KEY | API key for Mistral embeddings | Yes |
PORT | Server port | No (default: 3000) |
PUBLIC_URL | Public URL for config generation | No |
LOG_LEVEL | Log level: DEBUG, INFO, WARN, ERROR | No (default: INFO) |
#### Cursor / Claude Desktop
Add to your MCP configuration:
{
"mcpServers": {
"gruenerator": {
"url": "http://localhost:3000/mcp"
}
}
}After configuration, you can ask questions like:
| Endpoint | Method | Description |
|---|---|---|
/mcp | POST | MCP communication |
/mcp | GET | SSE stream |
/mcp | DELETE | End session |
/health | GET | Health check with cache and request statistics |
/metrics | GET | Detailed server metrics |
/.well-known/mcp.json | GET | Auto-discovery metadata |
/config/:client | GET | Generate client configuration |
/info | GET | Server information |
{
"status": "ok",
"service": "gruenerator-mcp",
"version": "1.0.0",
"collections": ["oesterreich", "deutschland", "bundestagsfraktion", "gruene-de", "gruene-at", "kommunalwiki", "boell-stiftung"],
"uptime": { "ms": 3600000, "hours": 1.0 },
"cache": {
"embeddingHitRate": "65%",
"searchHitRate": "42%"
},
"requests": { "total": 150, "searches": 120, "errors": 0 },
"performance": { "avgResponseTimeMs": 250, "cacheHitRate": "65%" }
}{
"server": { "name": "gruenerator-mcp", "version": "1.0.0" },
"uptime": { "hours": 1.0 },
"requests": { "total": 150, "searches": 120 },
"breakdown": {
"byCollection": { "deutschland": 40, "oesterreich": 30, "kommunalwiki": 25, "bundestagsfraktion": 20, "gruene-de": 15, "gruene-at": 20 },
"bySearchMode": { "hybrid": 100, "vector": 15, "text": 5 }
},
"cache": {
"embeddings": { "entries": 50, "hitRate": "65%" },
"search": { "entries": 30, "hitRate": "42%" }
},
"memory": { "heapUsedMB": 45, "rssMB": 120 }
}#### gruenerator_search
Searches party programs and content with hybrid, vector, or text search.
Parameters:
| Parameter | Type | Description | Default |
|---|---|---|---|
query | string | Search term or question | required |
collection | string | Collection to search (see table above) | required |
searchMode | string | hybrid, vector, or text | hybrid |
limit | number | Maximum number of results (1-20) | 5 |
filters | object | Metadata filters (see below) | optional |
useCache | boolean | Use cache | true |
Available Filters by Collection:
| Filter | Collections | Description |
|---|---|---|
documentType | oesterreich, deutschland | Document type (grundsatzprogramm, wahlprogramm, eu-wahlprogramm) |
title | oesterreich, deutschland | Exact document title |
section | bundestagsfraktion, gruene-de, gruene-at | Content section (Positionen, Themen, etc.) |
article_type | kommunalwiki | Article type (literatur, praxishilfe, faq, etc.) |
category | kommunalwiki | Thematic category (Haushalt, Umwelt, etc.) |
content_type | boell-stiftung | Content type (artikel, dossier, atlas, schwerpunkt) |
topic | boell-stiftung | Topic (klima, feminismus, migration, digitalisierung, etc.) |
region | boell-stiftung | Geographic region (afrika, europa, asien, lateinamerika, etc.) |
Example:
{
"query": "climate protection and renewable energy",
"collection": "kommunalwiki",
"searchMode": "hybrid",
"limit": 5,
"filters": { "article_type": "praxishilfe", "category": "Umwelt" }
}#### gruenerator_get_filters
Discovers available filter values for a collection. Use this before filtering to know valid values.
Parameters:
| Parameter | Type | Description | Default |
|---|---|---|---|
collection | string | Collection to get filters for | required |
Example Response:
{
"collection": "KommunalWiki",
"collectionId": "kommunalwiki",
"description": "Municipal politics knowledge (Heinrich Böll Foundation)",
"filters": {
"article_type": {
"label": "Article Type",
"type": "keyword",
"values": ["literatur", "praxishilfe", "faq", "sachgebiet"],
"count": 4
},
"category": {
"label": "Category",
"type": "keyword",
"values": ["Haushalt", "Umwelt", "Verkehr", "..."],
"count": 25
}
}
}#### gruenerator_cache_stats
Shows cache statistics for embeddings and search results.
Parameters: None
Example Response:
{
"embeddings": { "entries": 50, "hits": 120, "misses": 30, "hitRate": "80%" },
"search": { "entries": 30, "hits": 80, "misses": 40, "hitRate": "67%" }
}#### get_client_config
Generates ready-to-use MCP configurations for various clients.
Parameters:
client (string, required) - claude, cursor, or vscodeThe server provides the following resources via MCP protocol:
| URI | Description |
|---|---|
gruenerator://system-prompt | Read first! Usage instructions for AI assistants |
gruenerator://info | Server information and capabilities |
gruenerator://collections | List of all available collections |
gruenerator://collections/{key} | Details of a specific collection (oesterreich, deutschland, bundestagsfraktion, gruene-de, gruene-at, kommunalwiki, boell-stiftung) |
Combines vector and text search with Reciprocal Rank Fusion (RRF). Best results for most queries.
Pure semantic search based on embeddings. Good for conceptual questions.
Classic text search with German optimizations. Good for exact terms or names.
Contributions are welcome! Here's how you can help:
Please ensure your PR:
MIT License - see LICENSE
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.