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

2. Install

Download pre-built binary from GitHub Releases:

| Platform | Download | |----------|----------| | Linux x86_64 | ocds-mcp-linux-x86_64.tar.gz | | macOS Apple Silicon | ocds-mcp-macos-arm64.tar.gz | | Windows x86_64 | ocds-mcp-windows-x86_64.zip |

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-mcp

Windows: 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-mcp

3. Configure your AI client

Claude Desktop — edit claude_desktop_config.json:

{
  "mcpServers": {
    "ocds": {
      "command": "ocds-mcp",
      "args": ["--api-key", "sk_live_YOUR_KEY_HERE"]
    }
  }
}

Claude Code — add .mcp.json to your project root:

{
  "mcpServers": {
    "ocds": {
      "command": "ocds-mcp",
      "args": ["--api-key", "sk_live_YOUR_KEY_HERE"]
    }
  }
}

Cursor — Settings → MCP Servers → Add:

Command: ocds-mcp
Args: --api-key sk_live_YOUR_KEY_HERE

LM Studio — Settings → MCP → Add Server:

Click + Add Server and choose STDIO
Fill in:
- Name: ocds
- Command: full path to the binary, e.g. /usr/local/bin/ocds-mcp
- Arguments: --api-key sk_live_YOUR_KEY_HERE
Click Save
In the chat, select a model that supports tool use and enable the ocds server

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 | |------|-------------| | search_text | Semantic search across all tenders | | list_releases | Filter and browse tenders by month, CPV code, category, value range | | get_release | Full tender details by OCID | | get_index_info | Database statistics and connectivity check | | create_company_profile | Create a matching profile for your company | | update_company_profile | Update an existing profile | | get_company_profile | View profile details | | list_company_profiles | List all your profiles | | delete_company_profile | Delete a profile | | match_tenders | 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 help

How It Works

LLM ←stdio→ ocds-mcp (local)
               │  Local: company profiles + sentence embedder
               │  Remote: searches, release queries
               └──HTTPS──→ Vergabe Dashboard API

The 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.

MCP Servers