Сервер MCP, который примерно отображает подмножество https://developer.parliament.uk/,, а также предлагает дополнительные возможности семантического поиска.

Архитектура

Этот проект предусматривает: MCP Server: сервер на базе FastMCP ** Пакет Python**: небольшой пакет Python для запроса и загрузки парламентских данных из https://developer.parliament.uk/ в Qdrant Qdrant: Векторная база данных для семантического поиска по данным Hansard и Parliamentary Questions. Claude Integration: Подключение к Claude Desktop через прокси-сервер mcp-remote

Особенности

Инструменты MCP

MCP Server предоставляет 13 инструментов для помощи в парламентских исследованиях:

Депутаты и выборы

1. • • get_election_results ** - Получить результаты выборов для избирательных округов или конкретных членов
2. • • search_members * * - Поиск членов Палаты общин или лордов по различным критериям (включая поиск по местоположению / почтовому индексу)
3. • • get_detailed_member_information * * - Получите полную информацию о членах, включая биографию, контакты, интересы, запись голосования и членство в комитете

Парламентская структура

4. • • get_state_of_the_parties * * - Получить состояние сторон для дома в определенную дату

Parliament MCP Server

An MCP server that roughly maps onto a subset of https://developer.parliament.uk/, as well as offering additional semantic search capabilities.

Architecture

This project provides:

• MCP Server: FastMCP-based server
• Python package: A small python package for querying and loading parliamentary data from https://developer.parliament.uk/ into Qdrant
• Qdrant: Vector database for semantic search over Hansard and Parliamentary Questions data.
• Claude Integration: Connect to Claude Desktop via mcp-remote proxy

Features

MCP Tools Available

The MCP Server exposes 13 tools to assist in parliamentary research:

Members & Elections

1. get_election_results - Get election results for constituencies or specific members
2. search_members - Search for members of the Commons or Lords by various criteria (includes location/postcode search)
3. get_detailed_member_information - Get comprehensive member information including biography, contact, interests, voting record, and committee membership

Parliamentary Structure

4. get_state_of_the_parties - Get state of the parties for a house on a specific date
5. list_ministerial_roles - Get exhaustive list of all government or opposition posts and their current holders
6. get_departments - Get reference data for government departments

Committees

7. list_all_committees - List all parliamentary committees by status and house
8. get_committee_details - Get comprehensive committee information including members, publications, evidence, and upcoming events
9. get_committee_document - Retrieve committee documents including oral evidence, written evidence, and publications

Parliamentary Business

10. search_parliamentary_questions - Search Parliamentary Written Questions (PQs) by topic, date, party, or member
11. search_debate_titles - Search through debate titles to find relevant debates
12. find_relevant_contributors - Find members who have contributed most on specific topics
13. search_contributions - Search Hansard parliamentary records for actual spoken contributions during debates

Quick Start (local qdrant)

You will need

• Docker and Docker Compose
• Node.js (for mcp-remote)
• Claude Desktop (or another MCP client)
• Azure OpenAI account with API access

Create a .env file by copying the .env.example in the project root and replace the necessary variables.

After configuring your .env file, run the following command for a one shot setup of the MCP server and the Qdrant database with some example data from June 2025.

make dev_setup_from_scratch

Once this is run, you can connect to the MCP server using this config

# Add this to your Claude Desktop config, or another MCP client:
# On macOS Claude Desktop config is located at `~/Library/Application\ Support/Claude/claude_desktop_config.json`
{
  "mcpServers": {
    "parliament-mcp": {