Skip to main content
Glama
Rechtspraak MCP Server

Rechtspraak MCP Server

by axyr

Rechtspraak MCP Server

MCP (Model Context Protocol) server for searching and analyzing Dutch case law from rechtspraak.nl. Provides advanced search capabilities with query expansion, legal synonyms, faceting, and citation analysis.

Table of Contents

Related MCP server: korean-law-mcp

Features

πŸš€ MCP Server

  • Advanced Search: Full-text search with query expansion and Dutch legal synonyms

  • Faceted Search: Filter by court, legal area, date range, and procedure type

  • Citation Analysis: Extract and analyze case citations (incoming and outgoing)

  • Similar Cases: Find similar cases using MoreLikeThis algorithm

  • Legal Article Search: Search cases by specific legal articles

  • Trend Analysis: Analyze temporal trends in case law

  • Query Expansion: Automatic expansion with legal terms and synonyms

  • Rate Limiting & Caching: Built-in governance layer for production use

πŸ“₯ Data Import

  • Fetch case law XML from rechtspraak.nl feeds

  • Extract links and download case files

  • Automated batch processing

πŸ“Š Indexing

  • Parse XML documents with structured sections

  • Enrich with metadata (court types, legal domains, procedures)

  • Full-text indexing in Solr

  • Schema management and validation

Architecture

src/
β”œβ”€β”€ mcp/              # MCP server (main feature)
β”‚   β”œβ”€β”€ mcp_server.py       # MCP server implementation
β”‚   β”œβ”€β”€ mcp_schemas.py      # Pydantic schemas for all tools
β”‚   β”œβ”€β”€ solr_adapter.py     # Solr query adapter with advanced features
β”‚   β”œβ”€β”€ governance.py       # Rate limiting & caching
β”‚   β”œβ”€β”€ legal_synonyms.py   # Dutch legal synonyms expansion
β”‚   └── reference_data.py   # Court/procedure reference data
β”‚
β”œβ”€β”€ importer/         # Data import from rechtspraak.nl
β”‚   β”œβ”€β”€ extract_links.py
β”‚   β”œβ”€β”€ fetch_link_files.py
β”‚   └── fetch_content.py
β”‚
β”œβ”€β”€ indexing/         # XML parsing and Solr indexing
β”‚   β”œβ”€β”€ xml_parser.py
β”‚   β”œβ”€β”€ solr_indexer.py
β”‚   β”œβ”€β”€ solr_setup.py
β”‚   └── reindex_all.py
β”‚
β”œβ”€β”€ cli.py           # CLI for indexing
└── config.py        # Configuration

Installation

Prerequisites

  • Python 3.13+

  • uv (Python package manager)

  • Docker & Docker Compose (for Solr)

Setup

  1. Clone the repository:

git clone <repository-url>
cd rechtspraak-solr
  1. Start Solr with Docker:

docker-compose up -d solr
  1. Install dependencies:

uv sync
  1. Configure environment variables (create .env from .env.example):

cp .env.example .env
  1. Setup Solr collection and schema:

uv run rechtspraak-setup

Usage

Interactive CLI

Run the interactive menu for all operations:

python main.py

Or use direct commands:

# Data pipeline
python main.py fetch-links 2023-01-01 2023-12-31
python main.py extract-links 2023-01-01 2023-12-31
python main.py fetch-content

# Indexing
python main.py reindex          # Full reindex (delete + setup + index)
python main.py index            # Index data only
python main.py fix-schema       # Configure schema only

# MCP server
python main.py mcp              # Start MCP server
python main.py test-mcp         # Test connection

# Utilities
python main.py health           # System health check
python main.py test-reference   # Test reference data

MCP Server

The MCP server supports two modes:

  1. Local Mode (stdio): For Claude Desktop/Code running on your machine

  2. HTTP Mode (SSE): For remote access via API

Local Mode - Configuration for Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "rechtspraak": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/rechtspraak-solr",
        "run",
        "rechtspraak-mcp"
      ],
      "env": {
        "SOLR_URL": "http://localhost:8983/solr",
        "SOLR_COLLECTION": "rechtspraak"
      }
    }
  }
}

Local Mode - Configuration for Claude Code

Add to your Claude Code config (.claude/settings.local.json in project):

{
  "mcp": {
    "servers": {
      "rechtspraak": {
        "command": "uv",
        "args": [
          "--directory",
          "/path/to/rechtspraak-solr",
          "run",
          "rechtspraak-mcp"
        ],
        "env": {
          "SOLR_URL": "http://localhost:8983/solr",
          "SOLR_COLLECTION": "rechtspraak"
        }
      }
    }
  }
}

HTTP Mode - Remote Access

For production deployment with remote access:

  1. Start HTTP server:

docker-compose up -d
  1. Configure nginx (see config/nginx.conf for complete example):

location /sse {
    proxy_pass http://127.0.0.1:8000/sse;
    proxy_http_version 1.1;
    proxy_set_header Connection '';
    proxy_buffering off;
}
  1. Security: Set MCP_API_KEY environment variable in your .env file

Connecting to Remote MCP Servers

Claude Desktop/Code only supports stdio transport natively, not SSE/HTTP. To connect to remote MCP servers, use the included mcp-sse-client.js bridge client:

Add to Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "rechtspraak": {
      "command": "node",
      "args": [
        "/path/to/rechtspraak-solr/mcp-sse-client.js"
      ],
      "env": {
        "BASE_URL": "https://rechtspraak-nl-mcp.knowably.ai",
        "SSE_PATH": "/sse",
        "API_KEY": "your-api-key-here"
      }
    }
  }
}

Optional environment variables for mcp-sse-client.js:

  • CLIENT_NAME - Custom client name (default: "mcp-sse-client")

  • VERBOSE - Enable detailed logging (set to "true")

  • MAX_RETRIES - Max connection attempts (default: 3)

  • RETRY_DELAY_MS - Delay between retries in milliseconds (default: 2000)

  • CONNECTION_TIMEOUT_MS - Connection timeout in milliseconds (default: 30000)

The bridge client acts as a local stdio process that Claude can communicate with, while internally translating requests to SSE/HTTP for the remote server. It includes automatic reconnection, configurable timeouts, and graceful error handling

Available MCP Tools

The server provides the following tools:

  • cases_search - Search cases with filters and faceting

  • cases_get_by_ecli - Get specific case by ECLI identifier

  • cases_expand_query - Expand query with legal synonyms

  • cases_highlight_passages - Extract relevant passages from a case

  • cases_rerank - Rerank cases by relevance

  • cases_get_similar - Find similar cases

  • cases_search_by_article - Search by legal article

  • cases_validate_ecli - Validate ECLI format

  • cases_bulk_get - Batch retrieve multiple cases

  • cases_analyze_trend - Analyze temporal trends

  • cases_get_statistics - Get comprehensive statistics

  • cases_get_court_stats - Compare courts

  • cases_get_citations - Extract citations

  • cases_compare - Compare multiple cases

  • cases_extract_entities - Extract legal entities

  • system_health - Check system health

Direct Entry Points

You can also use the entry points directly:

# Full reindex
uv run rechtspraak-reindex

# Index specific directory
uv run rechtspraak-index --data-dir ./data

# Setup collection and schema
uv run rechtspraak-setup

# Start MCP server
uv run rechtspraak-mcp

Development

Project Structure

  • MCP Server: Main feature providing search API via MCP protocol

  • Data Importer: Tools to fetch case law from rechtspraak.nl

  • Indexing: XML parsing and Solr indexing with enrichment

  • CLI: Command-line tools for management tasks

Testing

# Check MCP server
uv run rechtspraak-mcp

# Test indexing
uv run rechtspraak-index --data-dir ./test-data --verbose

Example Queries

Once connected to an MCP client (Claude Desktop/Code), you can ask:

  • "Search for cases about 'aansprakelijkheid' in the last 5 years"

  • "Find cases citing ECLI:NL:HR:2019:1234"

  • "What are the trends in 'arbeidsrecht' cases from 2015 to 2023?"

  • "Find similar cases to ECLI:NL:RBDHA:2020:5678"

  • "Search cases mentioning Article 6:162 BW"

  • "Compare courts Hoge Raad and Rechtbank Amsterdam for tax cases"

License

Do whatever you want

Available Tools

16 tools
cases_analyze_trendB

Analyze temporal trends in case law over time. Returns time-series data with insights on trend direction, peak periods, and growth patterns. Supports year/quarter/month granularity.

Inputs: query (required), start_year (required), end_year (required), granularity, +1 more.

cases_bulk_getA

Batch retrieve multiple cases by ECLI identifiers. Efficient way to fetch many cases in a single request (max 100).

Inputs: eclis (required), fields.

cases_compareA

Compare multiple cases side-by-side. Identifies similarities and differences in metadata, subjects, and procedures. Returns divergence score (0=identical, 1=completely different).

Inputs: eclis (required), comparison_aspects.

cases_expand_queryA

Expand a user query with Dutch legal synonyms, abbreviations, entities, and temporal hints. Returns structured must/should terms for better retrieval.

Inputs: query (required).

cases_extract_entitiesB

Extract entities from a case including cited cases, legal articles, monetary amounts, dates, and parties. Uses regex patterns for Dutch legal text.

Inputs: ecli (required), entity_types.

cases_get_by_ecliA

Retrieve a specific case by ECLI identifier with structured sections (Inhoudsindicatie, Overwegingen, Beslissing). Returns normalized metadata and paragraph-level anchors.

Inputs: ecli (required), section_selector.

cases_get_citationsA

Extract citations from a case. Returns both outgoing citations (cases this case cites) and incoming citations (cases that cite this case) with context snippets.

Inputs: ecli (required), include_context, direction.

cases_get_court_statsA

Compare statistics across multiple courts for a query. Returns case counts, date ranges, top subjects and procedures for each court.

Inputs: query (required), courts (required), date_from, date_to.

cases_get_similarA

Find similar cases using MoreLikeThis algorithm. Returns cases with similar content based on paragraphs and summary. Supports filtering by court and legal area.

Inputs: ecli (required), max_results, min_similarity, filters.

cases_get_statisticsA

Get comprehensive statistics for a search query including facet distributions (courts, legal areas, procedures), date ranges, and aggregate counts.

Inputs: query (required), filters, include_facets.

cases_highlight_passagesA

Extract the most relevant passages from a specific case for a given query. Returns paragraph-level snippets with anchors, ideal for compact context assembly.

Inputs: ecli (required), query (required), max_passages.

cases_rerankA

Rerank a list of cases by relevance to a query. Takes ECLI identifiers and returns calibrated scores with original ranks.

Inputs: query (required), eclis (required).

cases_search_by_articleA

Search for cases that mention a specific legal article (e.g., '6:162 BW', 'Art. 81 RO'). Returns cases with context snippets where the article is mentioned.

Inputs: article (required), interpretation, rows, start.

cases_validate_ecliA

Validate ECLI identifier format and check if case exists in database. Returns validation status and metadata if found.

Inputs: ecli (required).

system_healthA

Check system health, Solr connection status, rate limits, and cache statistics. Returns version and operational metrics.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 16 tools

    Disambiguation5/5

    Each tool targets a distinct function: search, retrieval, analysis, citations, entities, validation, and health checking. There is no ambiguity between tools; even similar-sounding ones like 'cases_get_statistics' and 'cases_get_court_stats' have clear differences.

    Naming Consistency5/5

    All tools except the single health check follow a consistent 'cases_verb' pattern, using snake_case for verbs. This predictability aids agent selection and understanding.

    Tool Count5/5

    With 16 tools covering search, retrieval, analysis, and validation, the count is well-scoped for a legal research server. No tool feels superfluous, and the set is neither too sparse nor bloated.

    Completeness4/5

    The tool surface covers core workflows: search, fetch, compare, analyze trends, extract citations/entities, and health check. Minor gaps exist, such as a dedicated tool to list available courts or legal areas, but these are indirectly supported via search filters.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      MCP server that enables searching and retrieving judicial decisions from the Uruguayan National Public Jurisprudence Database (BJN).
      -
    • A
      license
      A
      quality
      A
      maintenance
      MCP server for searching Swiss court decisions from federal and cantonal courts via entscheidsuche.ch. Enables full-text search, law reference lookup, and filtering by canton, court level, and date without API keys.
      8
      20 PyPI
      1
      MIT