Data Analytics MCP Repositories

Multiple common text classification models based on CNN, RNN, and pre-trained NLP architectures for sentiment analysis and text classification. Supports data preprocessing, training word embeddings, and implementing advanced models like Bi-LSTM, Transformer, ELMo, and BERT for improved classification accuracy.

Streamlines data ingestion into Logstash pipelines by integrating various input sources, facilitating enhanced data processing capabilities.

Provides up-to-date information about players, teams, and games for the NBA, NFL, and MLB. Queries detailed sports data dynamically to enhance applications or agents with real-time sports insights.

Summarize front-end learning materials and showcase small demo projects. Provides concise notes and practical examples for better understanding of front-end technologies.

Interact with the arXiv API to retrieve scholarly article metadata, download PDFs, and search for articles using natural language queries. Enhance research workflows by directly accessing arXiv content within a large language model environment.

Manipulate Excel files programmatically without Microsoft Excel installed. Create, read, modify workbooks, apply formatting, generate charts, and manage data ranges.

Scan and analyze web content, fetching pages in Markdown format, extracting links, and generating sitemaps for comprehensive site analysis.

Provides querying capabilities for package repositories such as PyPI, npm, crates.io, Docker Hub, and Terraform Registry, enabling searches for packages, Docker images, and modules. Facilitates package discovery and inspection through a unified protocol interface.

Integrates Azure AI services with Claude Desktop for enhanced search capabilities, enabling intelligent searches across indexed documents and the web while providing source citations. Offers two implementations: one that utilizes the Azure AI Agent Service for document and web searches, and another for direct access to Azure AI Search.

Implement a Retrieval-Augmented Generation system using ChromaDB to facilitate semantic similarity search and document retrieval through embedding generation. Enables users to create and query document collections for effective RAG workflows in Python.

Search and retrieve academic papers from the PubMed database using enhanced tools such as MeSH term lookup, publication statistics, and structured PICO-based evidence searches.

Executes R code, visualizes plots, and interacts with scientific data within stateful sessions. Supports multimodal outputs to enhance conversations around scientific topics.

Retrieve and process documentation through vector search, enabling AI models to integrate relevant context into their responses. Supports multiple sources and offers semantic search capabilities for enhanced information retrieval.

Interact with Cube semantic layers to retrieve and describe data from a Cube deployment. Provide data in JSON format for further processing and detailed descriptions of the available data.

Analyze individual file histories and changes in Git repositories, focusing on file-level forensics. Gain insights into file versions, diffs, and semantic patterns to understand file evolution.

Extract text from images, PDFs, and Word documents while performing OCR and document conversion tasks. Convert documents to Markdown format, and retrieve key information from files intelligently.

Perform advanced econometric analyses using R, including linear regression, panel data modeling, and various diagnostic tests. Facilitate data-driven decision-making through sophisticated statistical analyses.

Provides AI-powered customer support by processing queries in real-time and integrating with Glama.ai for context fetching and Cursor AI for response generation.

A collection of reference implementations for integrating Large Language Models (LLMs) with various tools and data sources, enabling secure and controlled access to enhance AI applications. Implemented using either the Typescript or Python MCP SDK, these servers demonstrate the extensibility of the Model Context Protocol.

Seamless access to Old School RuneScape Wiki content and game data through a standardized protocol. Enables searching wiki pages, retrieving detailed page information, and querying various game data files to enhance applications with OSRS context.

Organize and analyze quantitative research data by tracking hypotheses, managing datasets, and documenting statistical analyses for insight generation. Facilitate context management across different research projects with a domain-specific knowledge graph.

Enables seamless YARA rule-based threat analysis and management for AI assistants, focusing on file analysis and standardized interactions for enhanced security in threat detection.

Access and manipulate financial datasets with ease, retrieving data as Pandas dataframes or numpy arrays for analysis and visualization. Seamlessly upload custom datasets to Quandl using minimal code.

Explore and manage Keboola Connection projects, including browsing buckets, tables, and components. Query tables directly, manage configurations, and trigger jobs through integration with AI tools.

Tracks newly created liquidity pools on Uniswap across nine blockchain networks in real-time, providing data for DeFi analysis and trading decisions. Enables querying and sorting of pools by various metrics such as timestamp, transaction count, volume, or TVL.

Provides comprehensive financial insights and analysis by leveraging real-time market data, including detailed ticker reports, options data, historical price trends, financial statements, and institutional ownership information.

Access and query UNHCR refugee statistics, enabling insights into forcibly displaced population trends. Filter data by country of origin, country of asylum, and year, while retrieving Refugee Status Determination application and decision data.

Index and query technical documentation using AI-powered semantic search. It crawls, processes, and embeds documentation for efficient retrieval through AI IDEs with built-in MCP tools for seamless integration.

Connects AI models to Typesense collections for efficient data discovery, search, and analysis using advanced search capabilities.

Search for French companies using text and geographic criteria, accessing essential information such as name, SIREN, SIRET, and activity codes. Perform searches within a specified radius and paginate through results.