"RAG (Retrieval-Augmented Generation) system that can store papers and web pages" matching MCP servers:

Enables local read-only search and retrieval of approved, current evidence via hybrid lexical and dense methods, with tools to get exact source spans, answer from cited passages, and create and verify recheckable evidence packets.

MCP server for App Store Connect that enables reading app/version data, analytics reports, sales/finance reports, and safely preparing metadata updates via natural language.

Enables fetching any public web page through managed proxies, with optional JavaScript rendering, returning markdown, text, HTML, or structured JSON.

Exposes a synthetic issue tracker and pipeline warehouse as callable tools so an agent can answer operational questions about tickets, pipeline health, runs, incidents, and governed metrics with every claim cited to the exact tool call it came from. All writes are proposal-only, requiring human approval through a gated apply path that logs each step for audit.

Exposes local DuckDB pizza sales data as MCP tools for querying store-level and total sales metrics via natural language, enabling local LLMs to perform real-time analytical queries.

Enables AI agents to generate UNHCR-styled data visualizations including bar, line, pie, and scatter charts with refugee and population data, returning charts as base64-encoded images.

Enables users to preprocess, analyze, and visualize CSV data through comprehensive tools for data manipulation, statistical analysis, and graph generation.

This server facilitates scalable discovery and execution of OpenAPI endpoints using semantic search and high-performance processing, overcoming limitations of large spec handling for streamlined API interactions.

Enables AI to interact with Microsoft Access (.mdb, .accdb) and SQLite 3 databases, including read-only support for Access 97 databases. Supports executing SQL queries, importing/export data from CSV and Excel files, and storing notes about database files.

Provides stock market data and computes technical indicators like EMA, MACD, and RSI across multiple timeframes using the LongPort API and TA-Lib. It enables users to perform detailed financial analysis and multi-timeframe market reviews through standard MCP tools.

Enables schema-aware exploration of JSON data by uploading samples, flattening nested structures, and using heuristic search with token overlap and fuzzy matching to find field paths for target names, accelerating ETL and API onboarding workflows.

Offline-first MCP server for TwitterAPI.io docs (endpoints, pages, blogs) with fast fuzzy search.

Enables language models and users to perform exact arithmetic, symbolic math, unit/date conversions, statistics, and read-only SQL queries over registered files, with every operation logged by a citable ID that humans can re-run.

MCP server that exposes local Python scripts as tools for AI clients (e.g. Claude Desktop), enabling directory tree generation, Excel-to-text conversion, Python code extraction, and text file merging.

An enterprise-grade data analysis system that enables users to discover data sources, configure analyses, and execute workflows through Claude Desktop. It features intelligent caching, session isolation, and secure JWT authentication for streamlined multi-user data orchestration.

Aggregates personal data from multiple sources (Claude Code sessions, GitHub, Dropbox, etc.) into a searchable SQLite store and exposes query capabilities via FastMCP for models.

Fulcra is the world's best agent-first data platform, allowing you to easily and securely store your data in a context lake and connect it to any agent, anywhere. Use Fulcra to store personal data, coordinate your work with other agents, and more.

Data compression MCP server with auto-algorithm selection (gzip, brotli, deflate). 7 tools for compress, decompress, analyze, store, retrieve, list, and stats. Achieves 60x compression on docs, 30x on SQL. Lossless round-trip verified. Zero dependencies.

Enables unified querying of GA4, Cloudflare Web Analytics, Vercel Analytics, and Google Search Console through a single MCP interface, with cross-tracker comparisons and discrepancy reporting.

An MCP server that enables LLMs to detect and anonymize over 25 types of Personally Identifiable Information (PII) using Microsoft Presidio. It supports various redaction strategies and can process both plain text and structured data to help ensure data privacy.