Name: Parquet MCP Server
Author: DeepSpringAI

Question 1

What is the Parquet MCP Server?

Accepted Answer

The Parquet MCP (Model Control Protocol) Server is a tool that provides web search and similarity search functionalities, designed to work seamlessly with Claude Desktop. It enables AI applications to efficiently access and process information from the web.

Question 2

What is MCP?

Accepted Answer

MCP stands for Model Control Protocol. It's an open protocol that standardizes how applications provide context to LLMs, allowing AI models to interact with external data sources and tools.

Question 3

What are the main functionalities of the Parquet MCP Server?

Accepted Answer

The server offers two main functionalities: 1) Web Search: Perform web searches and scrape results. 2) Similarity Search: Extract relevant information from previous searches.

Question 4

How do I install the Parquet MCP Server?

Accepted Answer

You can install it either via Smithery using the command `npx -y @smithery/cli install @DeepSpringAI/parquet_mcp_server --client claude`, or by cloning the repository, setting up a virtual environment, and installing the package manually.

Question 5

What environment variables do I need to configure?

Accepted Answer

You need to create a `.env` file with variables like `EMBEDDING_URL`, `OLLAMA_URL`, `EMBEDDING_MODEL`, and API keys for search services such as `SEARCHAPI_API_KEY`, `FIRECRAWL_API_KEY`, and `VOYAGE_API_KEY`.

Question 6

How do I use the server with Claude Desktop?

Accepted Answer

Add the server configuration to your `claude_desktop_config.json` file, specifying the command and arguments to run the server.

Question 7

What are the available tools in the server?

Accepted Answer

The server provides two main tools: `Search Web` (to perform a web search and scrape results) and `Extract Info from Search` (to extract relevant information from previous searches).

Question 8

What parameters are required for the 'Search Web' tool?

Accepted Answer

The required parameter is `queries`, which is a list of search queries. An optional parameter is `page_number`, which defaults to 1.

Question 9

What parameters are required for the 'Extract Info from Search' tool?

Accepted Answer

The required parameter is `queries`, which is a list of search queries to merge.

Question 10

How do I test the MCP Server?

Accepted Answer

You can run the test suite in the `src/tests` directory using `python src/tests/run_tests.py` or run individual tests like `python src/tests/test_search_web.py`.

Question 11

What should I do if I encounter SSL verification errors?

Accepted Answer

Make sure the SSL settings in your `.env` file are correctly configured.

Question 12

What should I do if embeddings are not being generated?

Accepted Answer

Check that the Ollama server is running and accessible, the specified model is available, and the text column exists in your input Parquet file.

Question 13

What is UBOS?

Accepted Answer

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with LLM models, and create Multi-Agent Systems.

Question 14

How can I integrate Parquet MCP Server with UBOS?

Accepted Answer

By integrating the Parquet MCP Server with UBOS, you can enrich AI Agent context with real-time web information, automate data gathering and analysis, and build more intelligent and context-aware applications.

Question 15

Where can I find example prompts for using the server?

Accepted Answer

Example prompts are provided in the documentation for both Web Search and Extracting Info from Search functionalities.

Parquet MCP Server

Resources

Project Details

Recomended MCP Servers

Featured Templates

AI-Powered Product List Manager

Multi-language AI Translator

AI-Powered Essay Outline Generator

Image Generation with Stable Diffusion

AI Chat Bot: Text, Voice, and Video Magic

Pharmacy Admin Panel

Start your free trial