Data Analytics MCP Repositories

Bridge Dune Analytics data to AI agents by fetching and executing Dune queries, returning results in a user-friendly CSV format for easy processing.

Facilitates deep context extraction from local code repositories by analyzing code files and generating insights based on user queries. Utilizes advanced analysis tools to support targeted context generation and track token usage for optimized API performance.

Provides semantic code search capabilities by locally indexing codebases using ChromaDB. Enables efficient and context-aware code exploration for development tools.

Enforces data governance on top of LLM or other text-based pipelines, integrating Eunomia instruments with the Model Context Protocol.

Connects AI models to efficiently fine-tune large language models with reduced memory usage and increased speed. Supports advanced features like extended context lengths and quantization for optimal performance on consumer GPUs.

Integrate with the Yuque API for managing documents and user information. Supports creating, reading, updating, and deleting documents while providing access to analytics and statistics for knowledge bases.

Search for bioRxiv papers, retrieve detailed metadata, and download papers to support biological sciences research and analysis.

Provides civil engineering calculation tools including coordinate conversions between latitude/longitude and UTM/TWD97, Manning's coefficient lookup, soil pressure coefficient calculations, and drainage flow computations. Integrates seamlessly with LLM applications and AI tools for streamlined civil engineering workflows.

Utilizes a knowledge graph for dynamic information retrieval and storage, enhancing AI interactions by remembering user preferences and context. Integrates seamlessly with Neo4j for efficient data management.

Connects to ClinicalTrials.gov to search for and access detailed clinical trial information programmatically, facilitating efficient data retrieval for health sciences research and analysis.

Provides access to BigQuery for inspecting database schemas and executing SQL queries against datasets.

Provides advanced reasoning capabilities utilizing distilled models for enhanced performance in mathematical, coding, and reasoning tasks. Designed to assist in a variety of applications requiring sophisticated model interactions.

Explore RDF graphs and execute SPARQL queries on an Ontotext GraphDB instance for data retrieval and insights. It provides read-only access and enables interaction with various graphs in the repository.

Create a semantic memory layer on top of OpenSearch to facilitate LLM applications by integrating external data sources and tools.

Provides semantic search and analysis of Federal Reserve statements, enabling access to metadata, trend analysis of language usage, and retrieval of full statement content through a clean interface.

Analyze data from PostgreSQL databases or CSV files to calculate statistics and generate machine learning predictions based on user-defined parameters.

Facilitates seamless interaction between MCP clients and GraphQL APIs by providing tools for schema introspection and query execution. Supports secure connections using bearer token authentication when required.

Search for YouTube videos and analyze their content by generating summaries, retrieving subtitles, and pinpointing specific video segments. The tool supports keyword-based searches and provides detailed video metadata, intelligent subtitle selection, and content analysis powered by GPT.

Enables natural language querying of live Amazon Redshift data without the need for SQL, facilitating seamless data retrieval from Redshift through a simple MCP interface. Connects LLM-powered clients to query and explore Redshift data with built-in tools for schemas and execution.

OmniMCP enhances AI models with structured responses and visual analysis to automate UI operations. It provides rich UI context and interaction capabilities through the Model Context Protocol, facilitating precise user interface interactions.

Queries multiple AI models simultaneously to provide diverse perspectives on questions, synthesizing insights for enhanced decision-making. Integrates with Claude for a comprehensive advisory experience by combining various AI viewpoints.

Provides fast and efficient vector search capabilities for software projects, automatically indexing codebases and responding to search queries in real-time. Integrates seamlessly with LLM tools for enhanced coding agent performance without complex configurations.

Interact with GraphQL APIs by performing schema introspection and executing queries. Enhance applications through dynamic discovery and utilization of GraphQL capabilities.

Fetch web content in various formats such as HTML and JSON using intelligent scraping techniques while providing bilingual support for English and Chinese.

Search and explore proteomics datasets from the PRIDE Archive using structured queries. It facilitates the integration of AI models with biomedical research data for efficient data retrieval and analysis.

This server provides an easy way to analyze and visualize financial data of publicly listed companies using the DART API. It enables users to perform detailed financial analyses, compare companies, and assess financial risks with real-time data.

Build intelligent, document-based applications with integrated data retrieval capabilities, leveraging Retrieval-Augmented Generation (RAG) methodologies.

Integrates Google Ads data with Claude AI for analysis and reporting through natural language queries. Provides insights into campaign performance, metrics tracking, and ad management.

Enhances reasoning capabilities of LLMs by generating concise intermediate outputs, effectively reducing token usage and response time while maintaining accuracy across various reasoning tasks. Integrates with OpenAI's API for seamless workflows.

Retrieve and analyze data or run tasks using an in-memory SQLite database for efficient data processing. Supports data interaction through a Developer API with an ETL pipeline for handling data requests and queries.