What is an MCP server?
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Discover awesome MCP servers.
tqvthu-works
jonathanbulkeley
Sovereign cryptographic oracle — 131 Ed25519-signed endpoints across crypto prices, FX, metals, stablecoins, economic indicators, commodities, gas oracles, volatility/sentiment/stress/contagion indices, marine, weather, DeFi yield, and COT positioning. Pay-per-query via x402 (USD
lenderwiki
MCP server for LenderWiki — search, compare, and analyze 13,000+ US consumer lenders from any AI assistant
devopam
A safe-by-default PostgreSQL Model Context Protocol server for AI agents.
sunilemanjee
jeweis
这是一个mssql MCP服务器,专门用于执行Microsoft SQL Server的数据查询和表结构查询操作。该服务器提供了一系列工具,使客户端能够方便地与SQL Server数据库进行交互。
JaviMaligno
MCP server with 14 tools for PostgreSQL database operations. Query databases, explore schemas, analyze tables, list indexes/constraints, and get performance statistics. Features security-first design with SQL injection prevention and read-only mode by default. Works with Claude D
awmatheson
A MCP server based on Redis
ryudg
Just Read only
Adhikram
cbuehrle1
MCP-Mirror
Mirror of
cocaxcode
Talk to your databases in natural language. Multi-database MCP server (PostgreSQL, MySQL, SQLite) with 19 tools for connection management, schema introspection, query execution, rollback snapshots, and query history. Auto-discovers schema with FKs so AI agents can build JOINs fro
MCP-Mirror
Mirror of
MCP-Mirror
Mirror of
CDataSoftware
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Oracle SCM (beta): https://www.cdata.com/download/download.aspx?sku=KSZK-V&type=beta
spragginsdesigns
akramansaritorinit
rbatis
A database server based on Model Context Protocol (MCP), supporting SQLite, MySQL, PostgreSQL, and MSSQL databases.
sahil1115
Model Context Protocol for cassandra database
SoftwareTree
Database-agnostic MCP server that exposes relational databases as governed business objects (Customers, Orders, Products) for AI agents via ORM abstraction — instead of raw SQL or schema access. Works with any JDBC-compliant database (PostgreSQL, MySQL, Oracle, SQL Server, SQLite
yuru-sha
MCP Server for PostgreSQL databases
boyzoid
An MCP server for connecting to a MySQl database.
divyanshu-vashu
MCP-Mirror
Mirror of
RonHouben
MCP Server for postgres
syedasad-kiwi
A powerful Model Context Protocol (MCP) server implementation for MongoDB integration
burakdirin
An MCP server implementation that enables Claude AI to interact with Clickhouse databases.
Augmented-Nature
RollandMELET
Docker configuration for Qdrant MCP server
fkdevsoft
monochromegane
MCP BigQuery Server is a server that allows you to query BigQuery tables using MCP.
vuutla
pengcunfu
零负担、开箱即用的模型上下文协议(MCP)服务器,用于与 MySQL 交互和自动化操作。无需 Node.js 或 Python 环境。该服务器提供对 MySQL 数据库和表进行 CRUD 操作的工具,以及只读模式以防止意外的写入操作。您还可以通过添加 --with-explain-check 标志让 MCP 服务器在执行查询前使用 EXPLAIN 语句检查查询计划。
welove111
Live Bitcoin price, AI-powered predictions for 2027-2030 (82% accuracy across 4 halving cycles), halving countdown analytics, on-chain market signals, and Lightning donation tools. Free, open MCP server — no auth required for core tools.
Martyr2
Quick little template for a local MCP MySQL server.
comonetso
Model Context Protocol server for MySQL databases in Cursor IDE
SuMiaoALi
A general Mysql-MCP-Server
zhaoxin34
setyolegowo
MCP-Mirror
Mirror of
Popplywop
SQL Server MCP Server - Provides SQL Server database access via Model Context Protocol
the-nine-nation
a readonly clickhouse mcp server and ensure your ai use clickhouse safely
1Levick3
Mcp server for postgres
AndrewJDawes
Augmented-Nature
A comprehensive Model Context Protocol (MCP) server for accessing the STRING protein interaction database. This server provides powerful tools for protein network analysis, functional enrichment, and comparative genomics through the STRING API.
MCP-Mirror
Mirror of
zx8086
Jimmy974
CDataSoftware
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free [CData MCP Server for Amazon DynamoDB (beta)](https://www.cdata.com/download/download.aspx?sku=DDZK-V&type=beta).
MCP-Mirror
Mirror of
hirokita117
ローカル環境でQdrantとMCP-server-qdrantを簡単に立ち上げるためのDocker Compose設定
nsphung
A Snowflake MCP server — SQL queries, schema exploration, and data insights for AI assistants
ambakick
Swayingleaves
JhiNResH
jorekai
Ein Model Context Protocol (MCP) Server für die Deutsche Bahn Timetable API
NewToolAI
db-query-mcp is a mcp tool supporting diverse database querying and exporting.
CDataSoftware
This read-only MCP Server allows you to connect to Snowflake data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at
jamesg31
Common questions about MCP servers, tools, and integrations
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Every server's detail page includes ready-to-paste config snippets for Claude Desktop, Cursor, VS Code, and other common clients — most installs take just a couple of minutes.
Most servers listed here are free and open source. Some wrap third-party APIs (cloud services, paid data providers, etc.) that require your own API key or subscription.
A local MCP server runs on your device and usually connects over stdio, giving you more direct control over data but requiring a runtime and installation. A remote MCP server is hosted by a provider and connects over HTTP, making setup easier while adding network and provider availability dependencies.
Claude Desktop, Claude Code, Cursor, VS Code, Codex, and other AI clients that support the Model Context Protocol can connect to MCP servers. Configuration formats and supported transports vary by client.
Review the source repository, maintenance activity, dependencies, requested permissions, and data-handling documentation before installation, and prefer official or trusted maintainers. Use least-privilege credentials for sensitive access such as files, databases, shells, and production systems.