What can you do with this server?

The Parquet MCP Server is a tool for web searches and similarity comparisons that allows you to: * Perform web searches and scrape results based on provided queries * Extract relevant information from previous search results * Handle multiple search queries simultaneously with pagination support * Utilize PostgreSQL functionality for vector similarity searches * Integrate with Claude Desktop for AI-powered workflows * Extend functionality through smithery for automatic installation or manual configuration

Which integrations are available for this server?

Converts Parquet files to DuckDB databases for efficient querying and analysis Uses environment variables for configuration of embedding services, database connections, and model selection Stores embedding vectors as NumPy arrays in the Parquet file output Uses Ollama models to generate text embeddings from Parquet file columns Converts Parquet files to PostgreSQL tables with pgvector support for vector similarity search

How do I use parquet mcp server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@parquet mcp server search for 'latest macbook pro reviews' and scrape page 1 results" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

parquet_mcp_server

A powerful MCP (Model Control Protocol) server that provides tools for performing web searches and finding similar content. This server is designed to work with Claude Desktop and offers two main functionalities:

Web Search: Perform a web search and scrape results
Similarity Search: Extract relevant information from previous searches

This server is particularly useful for:

Applications requiring web search capabilities
Projects needing to find similar content based on search queries

Installation

Installing via Smithery

To install Parquet MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @DeepSpringAI/parquet_mcp_server --client claude

Clone this repository

git clone ...
cd parquet_mcp_server

Create and activate virtual environment

uv venv
.venv\Scripts\activate  # On Windows
source .venv/bin/activate  # On macOS/Linux

Install the package

uv pip install -e .

Environment

Create a .env file with the following variables:

EMBEDDING_URL=http://sample-url.com/api/embed  # URL for the embedding service
OLLAMA_URL=http://sample-url.com/  # URL for Ollama server
EMBEDDING_MODEL=sample-model  # Model to use for generating embeddings
SEARCHAPI_API_KEY=your_searchapi_api_key
FIRECRAWL_API_KEY=your_firecrawl_api_key
VOYAGE_API_KEY=your_voyage_api_key
AZURE_OPENAI_ENDPOINT=http://sample-url.com/azure_openai
AZURE_OPENAI_API_KEY=your_azure_openai_api_key

Related MCP server: MCP Log Reader

Usage with Claude Desktop

Add this to your Claude Desktop configuration file (claude_desktop_config.json):

{
  "mcpServers": {
    "parquet-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/home/${USER}/workspace/parquet_mcp_server/src/parquet_mcp_server",
        "run",
        "main.py"
      ]
    }
  }
}

Available Tools

The server provides two main tools:

Search Web: Perform a web search and scrape results
- Required parameters:
  - queries: List of search queries
- Optional parameters:
  - page_number: Page number for the search results (defaults to 1)
Extract Info from Search: Extract relevant information from previous searches
- Required parameters:
  - queries: List of search queries to merge

Example Prompts

Here are some example prompts you can use with the agent:

For Web Search:

"Please perform a web search for 'macbook' and 'laptop' and scrape the results from page 1"

For Extracting Info from Search:

"Please extract relevant information from the previous searches for 'macbook'"

Testing the MCP Server

The project includes a comprehensive test suite in the src/tests directory. You can run all tests using:

python src/tests/run_tests.py

Or run individual tests:

# Test Web Search
python src/tests/test_search_web.py

# Test Extract Info from Search
python src/tests/test_extract_info_from_search.py

You can also test the server using the client directly:

from parquet_mcp_server.client import (
    perform_search_and_scrape,  # New web search function
    find_similar_chunks  # New extract info function
)

# Perform a web search
perform_search_and_scrape(["macbook", "laptop"], page_number=1)

# Extract information from the search results
find_similar_chunks(["macbook"])

Troubleshooting

If you get SSL verification errors, make sure the SSL settings in your .env file are correct
If embeddings are not generated, check:
- The Ollama server is running and accessible
- The model specified is available on your Ollama server
- The text column exists in your input Parquet file
If DuckDB conversion fails, check:
- The input Parquet file exists and is readable
- You have write permissions in the output directory
- The Parquet file is not corrupted
If PostgreSQL conversion fails, check:
- The PostgreSQL connection settings in your .env file are correct
- The PostgreSQL server is running and accessible
- You have the necessary permissions to create/modify tables
- The pgvector extension is installed in your database

PostgreSQL Function for Vector Similarity Search

To perform vector similarity searches in PostgreSQL, you can use the following function:

-- Create the function for vector similarity search
CREATE OR REPLACE FUNCTION match_web_search(
  query_embedding vector(1024),  -- Adjusted vector size
  match_threshold float,
  match_count int  -- User-defined limit for number of results
)
RETURNS TABLE (
  id bigint,
  metadata jsonb,
  text TEXT,  -- Added text column to the result
  date TIMESTAMP,  -- Using the date column instead of created_at
  similarity float
)
LANGUAGE plpgsql
AS $$
BEGIN
  RETURN QUERY
  SELECT
    web_search.id,
    web_search.metadata,
    web_search.text,  -- Returning the full text of the chunk
    web_search.date,  -- Returning the date timestamp
    1 - (web_search.embedding <=> query_embedding) as similarity
  FROM web_search
  WHERE 1 - (web_search.embedding <=> query_embedding) > match_threshold
  ORDER BY web_search.date DESC,  -- Sort by date in descending order (newest first)
           web_search.embedding <=> query_embedding  -- Sort by similarity
  LIMIT match_count;  -- Limit the results to the match_count specified by the user
END;
$$;

This function allows you to perform similarity searches on vector embeddings stored in a PostgreSQL database, returning results that meet a specified similarity threshold and limiting the number of results based on user input. The results are sorted by date and similarity.

Postgres table creation

CREATE TABLE web_search (
    id SERIAL PRIMARY KEY,
    text TEXT,
    metadata JSONB,
    embedding VECTOR(1024),

    -- This will be auto-updated
    date TIMESTAMP DEFAULT NOW()
);

parquet mcp server