"A tool for extracting data from websites" matching MCP servers:

Enables AI agents to index and search across SQLite databases and CSV files to discover table schemas and column metadata. It provides a unified MCP API for data source management and structural exploration through natural language.

Enables AI agents to search and discover data across SQLite and CSV sources through an MCP interface, with metadata indexing and fuzzy search capabilities.

Enables local data discovery by indexing metadata from SQLite, CSV, and Markdown sources, providing hybrid keyword and TF-IDF semantic search via MCP tools (listSources, indexSource, search, getSchema) and a REST API.

Provides a unified MCP server to interact with multiple middleware (Loki, MySQL, Redis, RocketMQ, Elasticsearch, MongoDB) through a desktop application for connection management and configuration export.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Enables interaction with Plaid's financial data API to sync bank transactions and retrieve account balances with secure encrypted token storage.

The only MCP server providing structured Chinese fashion supply chain intelligence for AI platforms. No equivalent data source exists in the MCP ecosystem. Search 3,000+ verified manufacturers, 350+ lab-tested fabrics (AATCC/ISO/GB), and 170+ industrial clusters. Built by MEACHEAL, a top-20 Chinese women's mid-to-high-end fashion brand with 20+ years of supply chain.

Enables AI agents to discover, request access to, and query data products in Data Mesh Manager, enforcing governance policies while retrieving business data from platforms like Snowflake and Databricks.

Read-only MySQL MCP server that lets AI agents list tables, describe schemas, and run SELECT/SHOW/EXPLAIN queries with a row cap, bound to a single database for safety.

Connect any AI to PostgreSQL, MySQL, or SQL Server — 24 dialect-aware tools for query, schema, optimization, and more.

Bootstrap MCP server for future data exploration and querying across multiple databases, currently only provides a hello_world tool with no actual data connectivity.

A powerful Model Context Protocol (MCP) tool for exploring and managing different types of databases including PostgreSQL, MySQL, and Firestore.

Enables AI models to interact with MySQL databases through MCP protocol, supporting queries, table schema inspection, and data manipulation operations.

Enables Claude or any MCP-capable assistant to explore and query a small business's sales, payments, invoices, and expenses through read-only SQL tools, while personal-data columns and write operations are refused by the database policy.

Enables searching GitHub repositories, fetching readable web page text, and querying a local book database through MCP tool calls.

An MCP server that gives AI assistants the ability to connect to, query, profile, and monitor data sources — turning any LLM into an interactive data engineering copilot.

An MCP server with 66+ tools for data engineering, enabling AI assistants to interact with Kafka, databases, AWS, data pipelines, infrastructure, and more.

Enables AI assistants to query relational databases like MySQL, PostgreSQL, and Oracle using natural-language questions, dynamically discovering schemas and generating validated read-only SQL through configurable AI providers such as Groq, Claude, and Gemini.

Give your AI agent the entire China A-share market: 55 datasets of prices, financials, capital flows, corporate events and futures/options, stored locally and queryable with read-only SQL. Built point-in-time with delisted stocks kept, so backtests don't lie — no account, no API key.

Enables agents to discover, inspect, and query municipal open datasets from data.seattle.gov through Socrata SODA2, with bounded reads, aggregates, and reference guidance.

Model Context Protocol (MCP) server providing access to 155 normalized Japanese public open datasets (10.16M+ records) including GEPS procurement, healthcare, land prices, and DuckDB SQL.

An MCP server that lets an LLM query a DuckDB warehouse of EuroLeague and EuroCup basketball data in natural language, offering tools for player and team stats, shot charts, boxscores, and fantasy draft analysis without contacting upstream APIs.

MCP server that profiles local data files (CSV, Parquet, JSON, Excel) and returns compact structured summaries with data-quality flags, enabling AI agents to understand datasets without seeing raw rows.

Read-only MCP server for querying ClickHouse (product telemetry) and Elasticsearch (download analytics), built for Percona VISTA.

MCP server providing AI assistants access to Polish public registries (KRS, CEIDG) and statistical data (GUS BDL) for querying companies, sole proprietorships, and regional statistics.

Enables agents to explore a database safely and read-only through three tools — list_tables, describe_table, and run_query — served over stdio. Queries are guarded by lexical validation, a capped LIMIT, a read-only SQLite connection, and an authorizer with a timeout.

Lets AI agents and developers inspect and query local MySQL, Redis, and MongoDB instances over STDIO or authenticated loopback HTTP, with read-only defaults and allowlisted non-production writes that require explicit opt-in. Production connections always reject writes, and database-enforced read-only accounts are recommended.

An MCP server for internal data platforms that enables search, viewing, tracing, and read-only querying of business assets like dashboards, metrics, and events.

An MCP server for interacting with SQL Server databases that enables schema inspection, record counting, and paginated data retrieval. It provides tools to explore table structures and fetch specific records while enforcing safety limits on data volume.

Enables answering questions about Ukrainian open data from the data.gov.ua CKAN portal by searching datasets, inspecting resource schemas, and running read-only SQL aggregates over a single tabular resource. Every data-backed answer is computed from retrieved data and returned with machine-readable provenance, and unsupported or unanswerable requests are refused rather than guessed.