Databases MCP servers

This MCP is a wrapper around the Instant Platform SDK. Add this MCP to your editor to enable creating, managing, and updating your InstantDB applications. Instant hosts the latest version of the server at https://mcp.instantdb.com. For modern clients that support streamable HTTP use https://mcp.instantdb.com/mcp. For legacy clients that require SSE use https://mcp.instantdb.com/sse. For more editor-specific instructions, see the public docs. If you haven't already, make sure to get a personal access token from your Instant dashboard.

3 tools · Connect via remote or local server, Create and manage InstantDB apps

Jitsu collects event data from your websites, apps and servers, and delivers it to your data warehouse and to whatever other tools you use. It covers the same ground as Segment, but it's MIT-licensed and self-hostable, so the whole pipeline can run inside your own infrastructure — or on Jitsu Cloud, same software, hosted. Data lands in minutes, not hours: Segment loads warehouses once or twice a day (hourly at best), while Jitsu delivers per destination in batches as frequent as a minute, or row-by-row where that suits the destination. And where Segment bills by Monthly Tracked User, Jitsu Cloud bills by event volume, so the bill tracks data rather than audience size — while self-hosting has no usage billing at all.

4 tools · Configure destinations and streams, Debug pipelines with Live Events

This is a Model Context Protocol (MCP) server that provides access to stock market data from Financial Datasets. It allows Claude and other AI assistants to retrieve income statements, balance sheets, cash flow statements, stock prices, and market news directly through the MCP interface. This MCP server provides the following tools: - get_income_statements: Get income statements for a company. - get_balance_sheets: Get balance sheets for a company. - get_cash_flow_statements: Get cash flow statements for a company. - get_current_stock_price: Get the current / latest price of a company. - get_historical_stock_prices: Gets historical stock prices for a company. - get_company_news: Get news for a company. - get_available_crypto_tickers: Gets all available crypto tickers. - get_crypto_prices: Gets historical prices for a crypto currency. - get_historical_crypto_prices: Gets historical prices for a crypto currency. - get_current_crypto_price: Get the current / latest price of a crypto curre

6 tools · get_balance_sheets, get_cash_flow_statements

AI-optimized PostgreSQL expertise for coding assistants pg-aiguide helps AI coding tools write dramatically better PostgreSQL code. It provides: - Semantic search across the official PostgreSQL manual (version-aware) - AI-optimized “skills” — curated, opinionated Postgres best practices used automatically by AI agents - Extension ecosystem docs, starting with TimescaleDB, with more coming soon - Agent Skills via npx skills — works with Claude Code, Cursor, Codex, Gemini CLI, and 40+ other agents - a public MCP server that can be used with any AI coding agent, or - a Claude Code plugin optimized for use with Claude's native skill support.

3 tools · search_docs, tiger

Connect AI assistants to your data using DuckDB's powerful analytical SQL engine. Supports connecting to local DuckDB files, in-memory databases, S3-hosted databases, and MotherDuck. Allows executing SQL read- and write-queries, browsing database catalogs, and switching between different database connections on-the-fly. Looking for a fully-managed remote MCP server for MotherDuck? → Go to the MotherDuck Remote MCP docs > 📝 Migrating from v0.x? > - Read-only by default: The server now runs in read-only mode by default. Add --read-write to enable write access. See Securing for Production. > - Default database changed: --db-path default changed from md: to :memory:. Add --db-path md: explicitly for MotherDuck. > - MotherDuck read-only requires read-scaling token: MotherDuck connections in read-only mode require a read-scaling token. Regular tokens require --read-write.

5 tools · Connect to MotherDuck for cloud analytics, Control query output size

http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. --> Apache Doris MCP Server exposes read-only Apache Doris capabilities to MCP Hosts and AI agents over MCP 2026-07-28. Version 1.0 replaces a large flat tool surface with eight stable domains and fifty-five progressively disclosed child capabilities, while keeping runtime availability, authorization, input schemas, output schemas, and failure behavior explicit.

6 tools · doris_catalog, doris_cluster

The StarRocks MCP Server acts as a bridge between AI assistants and StarRocks databases. It allows for direct SQL execution, database exploration, data visualization via charts, and retrieving detailed schema/data overviews without requiring complex client-side setup. - Direct SQL Execution: Run SELECT queries (read_query) and DDL/DML commands (write_query). - Database Exploration: List databases and tables, retrieve table schemas (starrocks:// resources). - System Information: Access internal StarRocks metrics and states via the proc:// resource path. - Detailed Overviews: Get comprehensive summaries of tables (table_overview) or entire databases (db_overview), including column definitions, row counts, and sample data. - Data Visualization: Execute a query and generate a Plotly chart directly from the results (query_and_plotly_chart). - Intelligent Caching: Table and database overviews are cached in memory to speed up repeated requests. Cache can be bypassed when needed. - Flexible Co

6 tools · Explore database schemas, query_and_plotly_chart

Model Context Protocol (MCP) Server Collection for OceanBase Ecosystem awesome-oceanbase-mcp is a Model Context Protocol (MCP) server repository specifically designed for the OceanBase ecosystem. 🎯 Mission: Enable AI assistants to interact directly with OceanBase databases and ecosystem components through standardized MCP protocols. ✨ Core Values: - 🤖 AI-Friendly: Direct database operations within Claude, ChatGPT and other AI assistants - 🔒 Secure & Reliable: Provides safe database access and operation mechanisms - 🛠️ Complete Ecosystem: Covers the complete OceanBase product and tool chain - 🚀 Ready to Use: Simple configuration to get started

5 tools · Diagnose performance issues, Manage cloud database instances

Pre-requisites: Teradata database (or free sandbox) + uv Add this to claude_desktop_config.json (Settings > Developer > Edit Config): - FastMCP v3 — Guaranteed resource cleanup with improved lifespan management - Hooks Capability — Intercept tool calls for custom monitoring, audit, or rate-limiting - Row Limit Protection — Configurable caps (DEFAULT_ROW_LIMIT, MAX_ROW_LIMIT) prevent LLM token overflow - Enhanced Security — VX views for fine-grained row-level access control Add Custom Logic Use hooks to intercept tool calls for monitoring, audit trails, or validation → Hooks Guide

4 tools · base, plot

The Model Context Protocol (MCP) is an open protocol designed to allow AI agents, IDEs, and automation tools to consume, query, and analyze structured data through context-aware APIs. This server wraps Blockscout APIs and exposes blockchain data—balances, tokens, NFTs, contract metadata—via MCP so that AI agents and tools (like Claude, Cursor, or IDEs) can access and analyze it contextually. - Contextual blockchain data access for AI tools - Multi-chain support via Blockscout PRO API configuration with Chainscout metadata enrichment - Versioned REST API: Provides a standard, web-friendly interface to all MCP tools. See API.md for full documentation. - Custom instructions for MCP host to use the server - Intelligent context optimization to conserve LLM tokens while preserving data accessibility - Smart response slicing with configurable page sizes to prevent context overflow - Opaque cursor pagination using Base64URL-encoded strings instead of complex parameters - Automatic truncation o

5 tools · get_address_by_ens_name, get_address_info

Airtable is the database and operations layer for your agents — whether running product, marketing, sales, ops, HR, or a custom business app. It combines structured data with multiplayer visual surfaces (grid, kanban, calendar, gallery, timeline) humans and agents share — plus sync integrations to Jira, Salesforce, Zendesk, Google Drive, Databricks, and the rest of your stack, all backed by enterprise governance. This repo is the canonical, official home for the plugins, skills, and other artifacts we ship to make Airtable as fluent to agents as it already is to builders and users. Today that ships as an installable plugin for Claude Code, Codex, and Cursor, and as a standalone collection of skills installable via the skills CLI for any agent that consumes agentskills.io–format skills.

4 tools · create_base, create_record

Hologres MCP Server serves as a universal interface between AI Agents and Hologres databases. It enables seamless communication between AI Agents and Hologres, helping AI Agents retrieve Hologres database metadata and execute SQL operations. Add the following configuration to the MCP client configuration file: Install MCP Server using the following package: Add the following configuration to the MCP client configuration file: The server supports Streamable HTTP transport for remote deployment scenarios where STDIO is not available.

6 tools · execute_hg_ddl_sql, execute_hg_select_sql

Model Context Protocol) (MCP) is a standardized protocol designed to manage context between large language models (LLMs) and external systems. This repository provides an installer and an MCP Server for Singlestore, enabling seamless integration. With MCP, you can use Claude Desktop, Claude Code, Cursor, or any compatible MCP client to interact with SingleStore using natural language, making it easier to perform complex operations effortlessly. 💡 Pro Tip: Not sure what the MCP server can do? Just call the /help prompt in your chat!

5 tools · create_notebook_file, get_user_info

> [!WARNING] > This local MCP server is deprecated. Use the hosted Atlan MCP at mcp.atlan.com/mcp instead. > > The local install path (Docker, uv, or pip install atlan-mcp-server) is in maintenance-only mode — no new features, support not guaranteed. The hosted endpoint is the recommended way to integrate Atlan with Claude Desktop, Cursor, Codex, Databricks UC, and other MCP clients. See the Atlan MCP overview for setup. The Atlan Model Context Protocol server allows your AI agents to interact with Atlan services.

6 tools · create_dq_rules, create_glossaries

- 🔍 Hybrid search — BM25 (full-text) + vector KNN (pgvector) fused via Reciprocal Rank Fusion - 📂 Multi-user — each user sees only their own memories; workspaces for shared team knowledge - 🛠️ 11 MCP tools — store, retrieve, recall, list, search by tag, get, update, delete, move, list workspaces, dream report - 💤 Dreaming — a guided consolidation pass (dream MCP prompt + dream_report tool): finds near-duplicate and conflicting memories, merges them into insights non-destructively, driven by the client LLM - 🌐 Web UI — browse, search, edit and delete memories in the browser; export/import JSON - 🔒 OAuth 2.1 — full in-process authorization server, always enabled - 🐘 PostgreSQL — pgvector for embeddings, tsvector for full-text search - 📊 Progressive disclosure — search returns compact snippets by default; call get_memory(name) only for what you need, reducing token usage - 🔁 Deduplication — automatically detects near-identical memories before saving, preventing noise accumulation

5 tools · dream, list_memories

A Model Context Protocol (MCP) server that provides tools to interact with Powerdrill datasets, authenticated with Powerdrill User ID and Project API Key. Please go to https://chat.powerdrill.ai/ for AI data analysis individually or use with your Team. If you have the Powerdrill User ID and Project API Key of your Team, you can manipulate the data via Powerdrill open sourced web clients: - Node.js edtion: https://flow.powerdrill.ai/, or play with the open source web client https://github.com/powerdrillai/powerdrill-flow. - Python edtion: https://powerdrill-flow.streamlit.app/, or play with the open source web client https://github.com/powerdrillai/powerdrill-flow-streamlit.

6 tools · mcp_powerdrill_create_data_source_from_local_file, mcp_powerdrill_create_dataset

Every AI conversation starts from zero. You repeat yourself to every agent — your name, your preferences, your allergies, your tech stack. Chat history is siloed per app. There's no portable memory layer. Epitome fixes this. One database that every AI agent shares, so they all remember you. 1. Sign up at epitome.fyi 2. Go to Settings → API Keys and copy your MCP URL 3. Connect an AI agent — done Open localhost:5173 and sign in with Google or GitHub OAuth. Get your API key from Settings → API Keys in the dashboard (hosted or self-hosted).

3 tools · memorize, recall

The official Model Context Protocol server for Coresignal — bring fresh B2B data on 895M+ employees, 70M+ companies, and 468M+ job postings straight into your AI assistant. Search in plain natural language, pull full records, enrich contacts with verified emails, and export large result sets as downloadable files — all from Claude, Cursor, Codex, VS Code, or any other MCP-compatible client. - OAuth 2.1 authentication — sign in with your Coresignal dashboard account; no API keys in config files. - Natural-language search with match evidence in every result row, so you can see why each record matched. - Cost transparency — every response reports credits_consumed, and expensive calls ask for confirmation before spending. - Field discovery — entity_fields finds the right field names by keyword, free, without loading the full 300+ field vocabulary into context. - File downloads — large result sets are stored server-side and returned as a download link instead of flooding the chat. - artifac

5 tools · artifact_read, email_enrich

Give your AI agents a memory they can trust. Engram lets your AI remember past conversations, facts, and decisions, so it feels more like a real teammate. This repository contains configuration templates for connecting MCP clients to Engram, a hosted memory service for AI agents. Engram is a hosted MCP server that provides reliable, explainable memory for AI agents: - Reliable memory: Agents remember conversations, facts, and decisions, with automatic knowledge graph extraction - Explainable retrieval: Every answer cites the memories and graph edges that justified it - Three-engine retrieval: BM25 + vector search + knowledge graph, fused and reranked - Bring your own model: All LLM calls route through your provider — no inference markup - Built-in controls: Organize memories into buckets, manage retention, and query with natural language

4 tools · list_buckets, list_memories

📇 ☁️ — An MCP Server for creating and managing Postgres databases using Neon Serverless Postgres

5 tools · compare_database_schema, create_project

> Build AI agents that interact with your data securely. Connect databases, create governed views, and deploy MCP tools to any agent builder. Pylar is a secure data access layer for AI agents that enables interaction with structured data sources without requiring direct database access or complex API integrations. 1. Data Sources connect to Pylar (Snowflake, BigQuery, PostgreSQL, HubSpot, Salesforce, and more) 2. SQL View is created to govern exactly what data agents can access 3. MCP Tools are built on the view—multiple tools for different use cases 4. Tools publish to Agent Builders (Claude Desktop, Cursor, LangGraph, Zapier, Make, n8n, and more) 5. Evals monitors all tool interactions for observability and optimization

5 tools · Create governed SQL views, Generate MCP tools from natural language

A Qdrant MCP server

4 tools · Code snippet management, Read-only mode

MCP server to query your data warehouse (BigQuery, Snowflake, Redshift, Azure Synapse) with natural language. Connect Claude, ChatGPT, Copilot or Gemini to your marketing data and get instant SQL insights. - Natural Language to SQL: Ask questions in plain language, get SQL queries executed on your data warehouse - Multi-platform Support: Works with BigQuery, Snowflake, Redshift, and Azure Synapse - AI Assistant Compatible: Connect to Claude, ChatGPT, Gemini, Le Chat, or Copilot - Schema Discovery: Automatic schema detection and context building via RAG - Use Case Library: Save and reuse your favorite analyses - Secure: OAuth 2.0 authentication, read-only queries, per-project access control

6 tools · create_use_case, execute_query

How to Install the Query Streams Agent on Windows How to Install the Query Streams Agent on Linux How to Install the Query Streams Agent on macOS Query Streams Access Level Permissions: Complete User Role Management Guide How to Install the Query Streams Google Sheets Addon Nova Concierge Mode: A Personal Data Analyst for Every User Nova Taught Knowledge: How Verified Learning Works How Nova AI Learns Your Database Schema Automatically AI Data Analytics: Query Any Database Without a BI Tool BI and Data Analytics Without Tableau or Power BI Text to SQL: How Nova AI Turns Questions Into Database Queries AI Powered Analytics: Ask Questions, Get SQL + Charts Natural Language to SQL: How Nova AI Turns Questions Into Database Queries

5 tools · Automate data syncs, Connect SaaS APIs to spreadsheets

Try Scite MCP for free. Create an account to get started. After starting the app, ChatGPT will prompt you to sign in with your Scite account. To use Scite in your prompts, type @Scite to activate the connector. For best performance, refresh or reconnect the Scite connector before each session by clicking the ··· menu next to Scite and selecting "Reconnect". For example: "@Scite find papers on CRISPR gene editing". If Scite is not responding, try reconnecting the connector. ChatGPT may silently disconnect tools between sessions. Click the ··· menu next to Scite in your conversation and select "Reconnect" to restore the connection.

4 tools · Activate via connector, Reconnect the connector

Slingshot Aerospace · Official Slingshot hosted MCP (Slingshot MCP) Official Slingshot Slingshot Portal MCP server for space, satellite, and space data. Model Context Protocol integration for space domain awareness, satellite tracking, TLE, ephemeris, and anomaly detection via AI agents in Cursor and ChatGPT. Connect with a Portal org API key and active subscription to https://api.portal.slingshot.space/mcp. Illustrative SGSN and Seradata tools and Marketplace and Analytics categories below — full tool inventory: Developer Suite · Help Center.

5 tools · get_latest_tle, get_rocket_body

Official Supabase MCP server to connect AI assistants directly with your Supabase project and allows them to perform tasks like managing tables, fetching config, and querying data.

5 tools · create_table, database

Token Metrics integration for fetching real-time crypto market data, trading signals, price predictions, and advanced analytics.

Interact with Verodat AI Ready Data platform

The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and branches using the Model Context Protocol (MCP). - A hosted MCP server that runs alongside the Xata API — there is nothing to install or run locally. - Authenticated via OAuth in your browser, or with a Xata API key for headless environments. - Accessible from any MCP client that supports remote servers over Streamable HTTP. The server uses the Streamable HTTP transport. There is no SSE endpoint and no local (npm) version of the server.

6 tools · call_read_operation, describe_operation

Read-only MCP over the SQL database behind an ERP (Logo Tiger, Netsis, Mikro). The agent sees canonical entities like `orders`, never raw ERP tables, through a four-layer read-only guard that checks the statement, fails closed, and blocks side-effecting functions (`pg_read_file`, `xp_cmdshell`, …) — measured by a public 28-attack benchmark and an in-browser "break it" playground running the real guard via Pyodide.

Server implementation for Google BigQuery integration that enables direct BigQuery database access and querying capabilities

Local YDB MCP is a TypeScript stdio MCP server for operating Docker-based local-ydb deployments via local or SSH-backed profiles. Supports bootstrap, diagnostics, auth hardening, storage workflows, dump/restore, upgrades, and plan-first mutating operations.

Brazilian Census Bureau (IBGE) data server with 23 tools for demographics, geography, economics, and statistics. Covers localities, SIDRA tables, Census data, population projections, and geographic meshes.

A PostgreSQL Model Context Protocol (MCP) server acting as a robust persistent super memory, task tracker, and multi-agent coordination hub for AI assistants.

Nocodb database integration, read and write capabilities

Query and analyze Azure Data Explorer databases

Natural language to validated SQL engine with multi-connector support (PostgreSQL, MySQL, Snowflake, BigQuery, DuckDB), document QA, semantic caching, and self-hosted MCP server.

The MCP server that remembers your database — persists table/column annotations, an FK relationship graph, and searchable notes across sessions, so the model stops re-discovering your schema every time. PostgreSQL, MySQL, MSSQL, SQLite; read-only-enforced.

Local, contract-governed federation across files and databases (Postgres, Snowflake, BigQuery, DuckDB, Excel, and more) with read-only guards, PII masking, and per-column agent access.

Query SQLite, PostgreSQL, and MySQL in plain language — read-only by design, with column hiding/masking, row caps, per-query timeouts, cost-based rejection, and rate limiting.

📇 ☁️ — An MCP server that supports fetching data from a database using natural language queries, powered by XiyanSQL as the text-to-SQL LLM.

TDolphinDB database integration with schema inspection and query capabilities

Read-only trust layer for Postgres: the agent never writes SQL — twelve tools compile it from definitions you control, PII and secret categories are refused before the query runs, and every call lands in a tamper-evident SHA-256 audit chain.

VikingDB integration with collection and index introduction, vector store and search capabilities.

An MCP Server to connect to your Weaviate collections as a knowledge base as well as using Weaviate as a chat memory store.

A Go implementation of a Model Context Protocol (MCP) server for Trino

Search URDB's product integrity database for integrity scores, enshittification events, and change tracking across consumer products

An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP). This server is built with the FastMCP framework, which enables LLMs to explore and query SQLite databases with built-in safety features and query validation.

Built-in MCP server for ArcadeDB, a multi-model database (graph, document, key-value, time-series, vector) with SQL, Cypher, Gremlin, and MongoDB QL support.

Read-only SQL across PostgreSQL, MySQL, S3-compatible buckets and folders of Parquet/CSV/JSON — and one query can join across all of them, federated in-process by DuckDB. No tool writes: they are absent rather than disabled, and every tool declares `readOnlyHint`. Runs from connection strings alone as `docker run -i --rm slotix/stream-mcp postgres://…` or as a one-click Claude extension.

All-in-one MCP server for Postgres development and operations, with tools for performance analysis, tuning, and health checks

Official MCP server for InfluxDB 3 Core/Enterprise/Cloud Dedicated

MCP and MCP SSE Server that automatically generate API based on database schema and data. Supports PostgreSQL, Clickhouse, MySQL, Snowflake, BigQuery, Supabase

SQL Server MCP server with AST-based query validation, read-only safety, schema exploration, ER diagram generation, and DBA toolkit integration (First Responder Kit, DarlingData, sp_WhoIsActive).

Python Streamable HTTP Server you can run locally to interact with [memvid](https://github.com/Olow304/memvid) storage and semantic search.

DICOM integration to query, read, and move medical images and reports from PACS and other DICOM compliant systems.

Ground-truth Firestore schema context for AI coding agents. Stops Cursor, Claude, and Windsurf from hallucinating field names and queries. Scans live collections, returns real field names, types, and presence rates.

The Semantic Engine for Model Context Protocol(MCP) Clients and AI Agents

MCP Server implementation that provides Elasticsearch interaction

A Model Context Protocol (MCP) that provides access to the MongoDB Atlas API. This server wraps the `mongodb-atlas-api-client` package to expose MongoDB Atlas functionality through MCP tools.

Natural-language questions over Postgres, Oracle, Snowflake, Databricks, DuckDB and SQLite. The model only proposes SQL — shape, access, dialect and query plan are checked deterministically before any rows are read, and it refuses rather than guessing. `uv run mnemiq serve`

Manage dozens of SQL Server instances from one config file, grouped by client or environment and hot-reloaded, with execution plans, index audits and stored-procedure analysis

PostgreSQL over MCP, including databases behind an SSH bastion.

MySQL database integration in NodeJS with configurable access controls and schema inspection

Inspect and operate Redis-backed job queues (Asynq and BullMQ): per-state counts, job detail with decoded payload and last error, and faithful retry/delete running each library's own scripts. Read-only mode for production.

Oracle 12c–26ai with no `run-sql` tool. You select the PL/SQL packages, tables, sequences and your own tested SQL statements, and it generates a Java MCP server exposing exactly those as typed tools — each with a real JSON Schema derived from the procedure's signature, covering records, collections, `%ROWTYPE`s, REF CURSORs and any number of OUT parameters. Anything you did not select has no tool, no method and no class: it is absent from the binary rather than refused.

MCP server for Apache Kafka that allows LLM agents to inspect topics, consumer groups, and safely manage offsets (reset, rewind).

MCP server for interacting with [YDB](https://ydb.tech) databases

Supabase MCP Server with support for SQL query execution and database exploration tools

PostgreSQL MCP server with 14 tools for querying, schema exploration, and table analysis. Features security-first design with SQL injection prevention and read-only by default.

Universal SQLAlchemy-based database integration supporting PostgreSQL, MySQL, MariaDB, SQLite, Oracle, MS SQL Server and many more databases. Features schema and relationship inspection, and large dataset analysis capabilities.

A Model Context Protocol server for managing, monitoring, and querying data in [CockroachDB](https://cockroachlabs.com).

MongoDB integration that enables LLMs to interact directly with databases.

Serverless MariaDB Cloud DB MCP server. Tools to launch, delete, execute SQL and work with DB level AI agents for accurate text-2-sql and conversations.

Gives LLMs the ability to manage Prisma Postgres databases (e.g. spin up new databases and run migrations or queries).

MCP server for Google Sheets API integration with comprehensive reading, writing, formatting, and sheet management capabilities.

SQLite operations — query databases, inspect schemas, explain queries, and export data.

Query PostgreSQL, MySQL, Redshift and SQL Server over verified SSH / AWS SSM tunnels, with read-only enforcement, confined file exports, and pluggable secret providers (env, Vault, AWS Secrets Manager, RDS IAM). Published on the official MCP Registry.

DuckDB database integration with schema inspection and query capabilities

An MCP server for interacting with VictoriaMetrics database.

Airtable database integration with schema inspection, read and write capabilities

ClickHouse schema exploration, analytical queries & management — every statement classified read/write/destructive and gated by access mode, with row caps and audit. `npx -y @dockndevai/mcp-clickhouse`

An MCP server for generic Database Management System (DBMS) Connectivity via the Java Database Connectivity (JDBC) protocol

Natural language PostgreSQL queries with automatic streaming, read-only safety, and universal database compatibility.

A secure, tunnel-native database bridge for AI agents. Connects localhost & on-premise databases (MSSQL, etc.) to LLMs with AST-based query safety and PII masking.

Connect Redash to Claude — natural-language SQL with safety guards (blocks DROP/TRUNCATE, PII detection), BIRD-based smart table selection, plus saved queries, dashboards, widgets, and alerts.

Node.js-based MySQL database integration that provides secure MySQL database operations

🏎️ 🏠 A – user-friendly read-only mysql mcp server for cursor and n8n...

The PlanetScale CLI includes an MCP server that provides AI tools direct access to your PlanetScale databases.

BigQuery database integration with schema inspection and query capabilities

Official Appwrite MCP server. Connect via hosted OAuth at `https://mcp.appwrite.io/` (no API keys) or self-host with a project API key to manage databases, auth, users, functions, storage, messaging, and more.

Connect AI tools directly to Airtable. Query, create, update, and delete records using natural language. Features include base management, table operations, schema manipulation, record filtering, and data migration through a standardized MCP interface.

🏎️ 🏠 – A high-performance multi-database MCP server built with Golang, supporting MySQL & PostgreSQL (NoSQL coming soon). Includes built-in tools for query execution, transaction management, schema exploration, query building, and performance analysis, with seamless Cursor integration for enhanced database workflows.

MCP server for legacy MySQL 5.0–5.6: schema inspection and SELECT by default, with opt-in INSERT/UPDATE/DELETE/DDL. Live-verified against MySQL 5.0–8.0. `npx -y mysql-legacy-mcp`

An MCP server for generic Database Management System (DBMS) Connectivity via the Open Database Connectivity (ODBC) protocol

provides AI-powered PostgreSQL performance tuning capabilities.

MySQL database integration with configurable access controls, schema inspection, and comprehensive security guidelines

Manage and query Postgres databases, tenants, users, auth using LLMs

🐍 🏠 Universal database MCP server supporting multiple database types including PostgreSQL, Redshift, CockroachDB, MySQL, RDS MySQL, Microsoft SQL Server, BigQuery, Oracle DB, and SQLite.

Production-grade PostgreSQL MCP server with 100+ tools for catalog introspection, AST-validated safe query execution, index tuning, natural-language SQL, pgvector/TimescaleDB/AGE integrations, and HTTP/stdio transports.

Read-only access to PostgreSQL, Oracle, and SQL Server for AI agents: schema discovery, query validation, execution plans, benchmarking, and index/statistics analysis. JDBC drivers bundled.

Supabase MCP Server for managing and creating projects and organisations in Supabase

MSSQL database integration with schema inspection and query capabilities

Pinecone integration with vector search capabilities

MCP service for Tablestore, features include adding documents, semantic search for documents based on vectors and scalars, RAG-friendly, and serverless.

A general-purpose MCP server that lets AI work with multiple databases within clear boundaries. Supports PostgreSQL and MySQL today with schema discovery, sampling, read-only queries, and query-plan inspection.

Run queries against InfluxDB OSS API v2.

One MCP server for PostgreSQL, MySQL, and SQLite. Unified read-only tools (`list_databases`, `list_tables`, `describe_table`, `run_query`) across all three engines with two-layer read-only enforcement (SQL-text guard + DB-level read-only transactions). Install: `npx -y mcp-multi-db`.

Official MCP server for the S2.dev serverless stream platform.

Firebase services including Auth, Firestore and Storage.

Baserow database integration with table search, list, and row create, read, update, and delete capabilities.

Model Context Protocol (MCP) server that provides comprehensive SQLite database interaction capabilities.

Django ORM static-analysis MCP server. Nine read-only tools (`list_apps`, `list_models`, `describe_model`, `find_relations`, `cascade_preview`, `er_diagram`, `describe_migration_dependency`, `suggest_indexes`, `signal_graph`) that expose Django schema, relationships (FK/M2M/O2O, on_delete, related_name), migration deps, missing indexes, and signal graphs — no DB, no Django boot, no credentials. Companion to a VS Code / VSCodium / Cursor extension (Open VSX verified) and a `django-orm-lens` PyPI CLI. `pip install django-orm-lens[mcp]`.

Firebird database MCP server that reads connection details from [FlameRobin's](http://www.flamerobin.org/) config — no credential setup required. Access all locally registered databases in one session with full schema introspection, DDL/DML execution, execution plans, and missing index analysis.

Snowflake integration implementing read and (optional) write operations as well as insight tracking

Convex database integration to introspect tables, functions, and run oneoff queries ([Source](https://github.com/get-convex/convex-backend/blob/main/npm-packages/convex/src/cli/mcp.ts))

A Model Context Protocol Server for MongoDB

Fills a PostgreSQL database with synthetic test data generated from its live schema, so an agent can plan a seed, run it and follow it to completion without production data. Runs as `npx -y seedfast mcp`, published in the official MCP registry as `st.seedfa/seedfast`.

Connect any AI to PostgreSQL, MySQL, or SQL Server — 24 dialect-aware tools for query, schema introspection, optimization, migrations, PII scan, and more. Hosted MCP server with OAuth 2.0 + Bearer auth, free trial available.

TiDB database integration with schema inspection and query capabilities

Semantic gateway that turns mainstream databases into MCP services with business metadata enhancement and parameterized SQL tools.

Open-source MCP server for Snowflake from official Snowflake-Labs supports prompting Cortex Agents, querying structured & unstructured data, object management, SQL execution, semantic view querying, and more. RBAC, fine-grained CRUD controls, and all authentication methods supported.

A universal database MCP server supporting simultaneous connections to multiple databases. It provides tools for database operations, health analysis, SQL optimization, and more. Compatible with mainstream databases including MySQL, PostgreSQL, SQL Server, MariaDB, Dameng, and Oracle. Supports Streamable HTTP, SSE, and STDIO; integrates OAuth 2.0; and is designed for easy customization and extension by developers.

Your AI Assistant's Gateway to Google Sheets! 25 powerful tools for seamless Google Sheets automation via MCP.

Confluent integration to interact with Confluent Kafka and Confluent Cloud REST APIs.

An MCP server for generic Database Management System (DBMS) Connectivity via SQLAlchemy using Python ODBC (pyodbc)

MongoDB Lens: Full Featured MCP Server for MongoDB Databases

Retrieval over your own data with Infino (BM25 full-text, vector, hybrid, and SQL), an embedded engine on Apache Parquet over object storage.

Supports SSE, STDIO; not only limited to MySQL's CRUD functionality; also includes database exception analysis capabilities; controls database permissions based on roles; and makes it easy for developers to extend tools with customization

Provides comprehensive integration with your [VictoriaLogs instance APIs](https://docs.victoriametrics.com/victorialogs/querying/#http-api) and [documentation](https://docs.victoriametrics.com/victorialogs/) for working with logs, investigating and debugging tasks related to your VictoriaLogs instances.

🏎️ 🏠 – Easy to use, zero dependency MySQL MCP server built with Golang with configurable readonly mode and schema inspection.

Memgraph MCP Server - includes a tool to run a query against Memgraph and a schema resource.

Microsoft Dataverse MCP server with 63 tools for entity CRUD, FetchXML/OData queries, metadata inspection, workflow execution, audit logs, and Power Platform integration. Zero-config device code authentication.

Comprehensive MCP server for Apache Druid that provides extensive tools, resources, and prompts for managing and analyzing Druid clusters.

MCP server for the Tolk smart contract compiler on TON blockchain. Compile, syntax-check, and generate deployment deeplinks for TON contracts directly from AI assistants.

Simple Snowflake MCP server that works behind a corporate proxy. Read and write (optional) operations

Trino MCP Server to query and access data from Trino Clusters.

Secure MCP server for safe, read-only DB access by AI agents, with SQL guardrails, table allowlists, PII masking, and audit logs.

MCP server for Apache Kafka and Timeplus. Able to list Kafka topics, poll Kafka messages, save Kafka data locally and query streaming data with SQL via Timeplus

Production-ready MCP server for libSQL databases with comprehensive security and management tools.

Percona Operator for PostgreSQL: manage PostgreSQL + PgBouncer clusters, connection pooling, PostgreSQL tuning, backups/PITR, DR & major upgrades — safe-by-default access modes, cluster allowlists, protected clusters, restore/upgrade/delete gating, and typed confirmation. `npx -y @dockndevai/mcp-percona-pg`

MCP server for secure database access (PostgreSQL, MySQL, SQLite) with parameterized queries and schema inspection

Query SQL databases (SQLite, PostgreSQL, BigQuery, Databricks) in natural language through a business semantic layer — glossary, metrics, and a data dictionary grounded against your real schema.

🎖️ ☕ – Connect to any relational database, and be able to get valid SQL, and ask questions like what does a certain column prefix mean.

MCP-first operations toolchain for SQLite, Cloudflare D1, and Turso. Inspect, diff, migrate, monitor, back up, and repair databases over stdio. Read-only by default; writes are opt-in, dry-run first, and auto-snapshot before applying. `npx -y litescope mcp`

Query and analyze Prometheus, open-source monitoring system.

Governed PostgreSQL DBA operations — slow-query, bloat, and blocking-lock RCA, index management, vacuum/analyze, and replication lag (35 tools) with unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

An MCP server that executes SQL via ConnectorX and streams the result to a CSV or Parquet file. Supports PostgreSQL, MariaDB, BigQuery, RedShift, MS SQL Server, etc.

PostgreSQL database integration with schema inspection and query capabilities

3 tools · describe_table, list_tables

A Model Context Protocol server for interacting with Google Sheets. This server provides tools to create, read, update, and manage spreadsheets through the Google Sheets API.

SQLite database operations with built-in analysis features

2 tools · list_tables, query

The Redis official MCP Server offers an interface to manage and search data in Redis.

2 tools · get_key, scan_keys

Navigate your [Aiven projects](https://go.aiven.io/mcp-server) and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services

6 tools · aiven_application_deploy, aiven_docs_search

Enables AI agents and applications to access real-time and 20+ years historical financial market data through natural language queries.

Read and write access to your Baserow tables.

Chroma MCP server to access local and cloud Chroma instances for retrieval capabilities

6 tools · chroma_add_documents, chroma_create_collection

ClickHouse database integration with schema inspection and query capabilities

4 tools · Check server health, list_databases

Official CoinGecko API MCP Server for Crypto Price & Market Data, across 200+ blokchain networks and 8M+ tokens.

Introspect and query your apps deployed to Convex.

Couchbase MCP server provides unfied access to both Capella cloud and self-managed clusters for document operations, SQL++ queries and natural language data analysis.

5 tools · get_buckets_in_cluster, get_cluster_health_and_services

Official Model Context Protocol (MCP) server for Datalastic — real-time vessel tracking, port data, maritime weather, and maritime intelligence for any MCP-compatible AI client. The Datalastic MCP server exposes 25 tools across six categories: - Live vessel positions — track ships in real time by MMSI, IMO, or name - Vessel registry — specs, dimensions, flag, and tonnage for 750,000+ vessels - Port data — global port and terminal directory with UN/LOCODEs - Area search — all vessels currently within a radius of any point or port - Maritime weather — wave, swell, and sea conditions merged with atmospheric weather, with 7-day forecasts at any coordinates, port, or vessel - Maritime intelligence (Maritime Reports add-on) — ownership, inspections, casualties, dry dock, engine specs, sale & purchase transactions

6 tools · Access maritime intelligence records, find_ports

Fireproof ledger database with multi-user sync

5 tools · create_document, delete_document

MCP Server for querying GreptimeDB.

6 tools · create_pipeline, describe_table

Hydrolix time-series datalake integration providing schema exploration and query capabilities to LLM-based workflows.

4 tools · get_table_info, list_databases

The iGaming Tools MCP server lets an AI assistant read our iGaming data directly — slot games, providers, demos, specs, screenshots, regulators, news and jobs — with no API key. - Server URL: https://mcp.i-gaming.tools/mcp - Transport: Streamable HTTP · Auth: none (free) · Access: read-only An MCP client is any AI app (Claude, ChatGPT, Cursor…) that can use external tools. The URL above is the same everywhere — only where you paste it differs: everyday chat apps (Claude, ChatGPT) take it in a settings screen; coding tools (code editors, command-line apps) take it in a config file. Find yours below.

6 tools · get_provider_demand, get_regulator

Open source MCP server specializing in easy, fast, and secure tools for Databases.

4 tools · Custom SQL tools, list_tables

MCP Server for Milvus / Zilliz, making it possible to interact with your database.

6 tools · milvus_create_collection, milvus_get_collection_info

Model Context Protocol with Neo4j (Run queries, Knowledge Graph Memory, Manaage Neo4j Aura Instances)

6 tools · Design and visualize graph data models, Execute write Cypher statements