qune-tech/ocds-mcp
This server connects AI assistants to German public procurement (OCDS) data, enabling tender discovery, semantic search, and company profile-based matching with GDPR-compliant privacy.
Semantic tender search (
search_text): Natural language vector similarity search across all procurement tenders (German text works best); queries are embedded locally and matched remotely.List and filter tenders (
list_releases): Browse tenders filtered by month, CPV code, category, procurement method, value range, buyer name, NUTS region, deadline, EU funding status, award status, and more.Full tender details (
get_release): Retrieve complete OCDS release data for a specific tender by OCID, including buyer, parties, awards, and lot structure.Database statistics (
get_index_info): Check API connectivity and see counts of available releases, embeddings, and local company profiles.Company profile management: Create, update, view, list, and delete company profiles (name, description, CPV codes, categories, location) stored locally in SQLite; description changes auto-trigger re-embedding.
Tender matching (
match_tenders): Match a stored company profile against tenders using semantic KNN cosine similarity, with optional post-filtering by CPV, category, value, location, deadline, and more. Profile text stays local — only embedding vectors are sent to the API.
Works with Claude Desktop, Claude Code, Cursor, LM Studio, and other MCP-compatible AI assistants.
ocds-mcp
MCP server for German public procurement data (OCDS). Connects your AI assistant (Claude, GPT, etc.) to the Vergabe Dashboard API for semantic search, tender matching, and company profile management.
Your company profiles never leave your machine — only embedding vectors are sent to the API. GDPR-compliant by design.
Quick Start
1. Get an API key
Sign up at vergabe-dashboard.qune.de and create an API key (MCP or Enterprise plan required).
2. Install
Via npx (easiest — downloads the correct binary automatically):
npx @qune-tech/ocds-mcp --api-key sk_live_YOUR_KEY_HEREOr download pre-built binary from GitHub Releases:
Platform | Download |
Linux x86_64 | |
macOS Apple Silicon | |
Windows x86_64 |
Linux / macOS:
# Example for Linux x86_64 — adjust the filename for your platform
tar xzf ocds-mcp-linux-x86_64.tar.gz
sudo mv ocds-mcp-linux-x86_64 /usr/local/bin/ocds-mcpWindows: Extract the zip and move ocds-mcp-windows-x86_64.exe somewhere on your PATH (e.g. C:\Users\YOU\.local\bin\ocds-mcp.exe).
Or build from source:
git clone https://github.com/qune-tech/ocds-mcp.git
cd ocds-mcp
cargo build --release
# Binary at target/release/ocds-mcp3. Configure your AI client
Claude Desktop — edit claude_desktop_config.json:
Using npx:
{
"mcpServers": {
"ocds": {
"command": "npx",
"args": ["-y", "@qune-tech/ocds-mcp", "--api-key", "sk_live_YOUR_KEY_HERE"]
}
}
}Using the binary directly:
{
"mcpServers": {
"ocds": {
"command": "ocds-mcp",
"args": ["--api-key", "sk_live_YOUR_KEY_HERE"]
}
}
}Claude Code — add .mcp.json to your project root:
Using npx:
{
"mcpServers": {
"ocds": {
"command": "npx",
"args": ["-y", "@qune-tech/ocds-mcp", "--api-key", "sk_live_YOUR_KEY_HERE"]
}
}
}Using the binary directly:
{
"mcpServers": {
"ocds": {
"command": "ocds-mcp",
"args": ["--api-key", "sk_live_YOUR_KEY_HERE"]
}
}
}Cursor — Settings → MCP Servers → Add:
Using npx:
Command:
npxArgs:
-y @qune-tech/ocds-mcp --api-key sk_live_YOUR_KEY_HERE
Using the binary directly:
Command:
ocds-mcpArgs:
--api-key sk_live_YOUR_KEY_HERE
LM Studio — Settings → MCP → Add Server:
Click + Add Server and choose STDIO
Fill in:
Using npx:
Name:
ocdsCommand:
npxArguments:
-y @qune-tech/ocds-mcp --api-key sk_live_YOUR_KEY_HERE
Using the binary directly:
Name:
ocdsCommand: full path to the binary, e.g.
/usr/local/bin/ocds-mcpArguments:
--api-key sk_live_YOUR_KEY_HERE
Click Save
In the chat, select a model that supports tool use and enable the
ocdsserver
LM Studio requires models with tool-calling support (e.g. Qwen 2.5, Mistral, Llama 3.1+). Smaller models may not use all 10 tools reliably — 7B+ recommended.
Replace sk_live_YOUR_KEY_HERE with your actual API key.
Available Tools
Tool | Description |
| Semantic search across all tenders |
| Filter and browse tenders by month, CPV code, category, value range |
| Full tender details by OCID |
| Database statistics and connectivity check |
| Create a matching profile for your company |
| Update an existing profile |
| View profile details |
| List all your profiles |
| Delete a profile |
| Match a profile against all tenders with semantic similarity |
CLI Options
Usage: ocds-mcp [OPTIONS]
Options:
--db <DB> Local profiles database [default: profiles.db]
--data-dir <DIR> Data directory [default: data]
--api-url <URL> Vergabe Dashboard API [default: https://vergabe-dashboard.qune.de]
--api-key <KEY> API key [env: OCDS_API_KEY]
-h, --help Print helpHow It Works
LLM ←stdio→ ocds-mcp (local)
│ Local: company profiles + sentence embedder
│ Remote: searches, release queries
└──HTTPS──→ Vergabe Dashboard APIThe MCP server runs locally on your machine:
Company profiles are stored in a local SQLite database — they never leave your network.
Text embeddings are computed locally using a multilingual ONNX model (multilingual-e5-small, ~118 MB, auto-downloaded on first use).
Only embedding vectors (arrays of 384 floats) are sent to the API for search and matching — your profile text stays local.
Tender data is fetched from the API on demand.
Requirements
An API key from vergabe-dashboard.qune.de (MCP or Enterprise plan)
~200 MB disk space for the ONNX model (downloaded automatically on first run)
Internet connection to reach the API
License
MIT — see LICENSE.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/qune-tech/ocds-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server