OpenTK Model Context Protocol Server

What is OpenTK Model Context Protocol Server?

This MCP server is a bridge between large language models and Dutch parliamentary data. It provides access to documents, debates, and member information from the Tweede Kamer via a standardized interface, built as a wrapper around Bert Hubert's OpenTK project.

How to use OpenTK Model Context Protocol Server?

Run instantly with npx @r-huijts/opentk-mcp. For Claude Desktop, add the server to your claude_desktop_config.json using the npx command. Once configured, Claude can use all 17 tools to search, analyze, and retrieve parliamentary data.

Key features of OpenTK Model Context Protocol Server

• Search parliamentary documents with advanced query syntax (quotes, NOT, OR, NEAR)
• Access comprehensive MP profiles and committee memberships
• Retrieve full document content from PDF/Word with smart chunking
• NLP-powered relevance analysis and keyword extraction (v1.0.16)
• Dutch-optimized entity recognition for persons, parties, and organizations
• Track legislative cases, voting results, and upcoming activities

Use cases of OpenTK Model Context Protocol Server

• Compare party positions on policy topics like AI or climate using parliamentary sources
• Research an MP's voting record, motions, and committee involvement
• Triage large sets of documents by relevance without reading every full text
• Identify upcoming debates, committee meetings, and related documents
• Find which MPs serve on specific committees and their recent joint initiatives

FAQ from OpenTK Model Context Protocol Server

What are the runtime dependencies?

The server runs on Node.js and is installed via npm. It uses the @modelcontextprotocol/sdk and connects to Bert Hubert's tkconv service over HTTP.

Where does the parliamentary data come from?

It sources data from the tkconv service (https://berthub.eu/tkconv/), which provides a developer-friendly API to Dutch parliamentary information.

What transport does the server use?

It uses stdio transport as per the MCP specification, configured via npx or a local Node.js command.

Does it require authentication or API keys?

No authentication or API keys are mentioned; the server accesses a publicly available parliamentary API.

Can it retrieve full document content?

Yes, tools like get_document_content fetch content from PDF and Word documents with three reading modes (targeted, sequential, full).