German public procurement data (OCDS) — semantic search, tender…
@qune-tech
About German public procurement data (OCDS) — semantic search, tender…
MCP server for German public procurement data — semantic search and tender matching for Claude, GPT, Cursor, and LM Studio
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ocds": {
"command": "ocds-mcp",
"args": [
"--api-key",
"sk_live_YOUR_KEY_HERE"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is German public procurement data (OCDS) — semantic search, tender matching, company profiles?
A local MCP server that connects AI assistants (Claude, GPT, etc.) to the Vergabe Dashboard API for German public procurement. It enables semantic search, tender matching, and company-profile management while keeping query and profile text private on your machine.
How to use German public procurement data (OCDS) — semantic search, tender matching, company profiles?
Install via npx @qune-tech/vergabe-mcp --api-key sk_live_YOUR_KEY_HERE, download a pre-built binary from GitHub Releases, or build from source. Configure your AI client (Claude Desktop, Claude Code, Cursor, LM Studio) with the command and API key. You can also pass the key via the VERGABE_API_KEY environment variable.
Key features of German public procurement data (OCDS) — semantic search, tender matching, company profiles
- Semantic search across all tenders (query embedded locally)
- 11 tools: search, filter, manage profiles, match tenders
- Company profile creation, update, list, delete
- Local privacy: data never leaves your machine
- Multilingual ONNX model for embeddings (384-dim)
- Raw eForms XML and linked notice retrieval
Use cases of German public procurement data (OCDS) — semantic search, tender matching, company profiles
- Find tenders semantically relevant to your company’s description and interests
- Manage multiple company profiles to track different business sectors
- Automatically match profiles against all open tenders by vector similarity
- Browse and filter tenders by phase, CPV, value, deadline, buyer
- Integrate an AI assistant with German public procurement data without exposing query text
FAQ from German public procurement data (OCDS) — semantic search, tender matching, company profiles
What data leaves my machine?
Only embedding vectors (384 floats), the OCIDs you fetch, filter values, and your API key are sent to the API. Your query and profile text stay local.
What are the runtime requirements?
You need an API key from vergabe-dashboard.qune.de on an Enterprise plan, ~120 MB disk space for the ONNX model (downloaded automatically), and an internet connection to reach the API.
How is privacy ensured?
Text embeddings are computed locally with a multilingual ONNX model. Only the resulting vectors are sent to the API, not the original text. Company profiles are stored in a local SQLite database.
Where does the embedding model download from?
On first use the server downloads the model from huggingface.co (~118 MB). No user data is sent in this fetch. For air-gapped installs, place the model files manually in the cache directory.
Is the server free?
Yes, the local MCP server is free and open source (MIT license). The API key issuance requires an active Enterprise plan on the Vergabe Dashboard.
Frequently asked questions
What data leaves my machine?
Only embedding vectors (384 floats), the OCIDs you fetch, filter values, and your API key are sent to the API. Your query and profile text stay local.
What are the runtime requirements?
You need an API key from vergabe-dashboard.qune.de on an Enterprise plan, ~120 MB disk space for the ONNX model (downloaded automatically), and an internet connection to reach the API.
How is privacy ensured?
Text embeddings are computed locally with a multilingual ONNX model. Only the resulting vectors are sent to the API, not the original text. Company profiles are stored in a local SQLite database.
Where does the embedding model download from?
On first use the server downloads the model from huggingface.co (~118 MB). No user data is sent in this fetch. For air-gapped installs, place the model files manually in the cache directory.
Is the server free?
Yes, the local MCP server is free and open source (MIT license). The API key issuance requires an active Enterprise plan on the Vergabe Dashboard.
Basic information
More Memory & Knowledge MCP servers
Orcha
westonhancockOrcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age
OpenLore
aakarimServe your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab
PLUR
plur-aiAI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
Tempreon
TempreonPerson-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
Memory Bank MCP Server
alioshrA Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Comments