"How to create, read from, and write to a database" matching MCP servers:

Scaffold and audit Starter Series projects — MCP server, Claude Code skill, and CLI in one package.

Sits between an AI agent and its MCP servers. Reads pass, writes are checked against your lists, and a read-only server refuses every write.

Enables read-write management of Microsoft Intune devices and group memberships via the Microsoft Graph API, including device property updates, remote actions, and group membership changes.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Read-only security audit for Supabase. Surfaces RLS gaps, permissive policies, exposed functions and grants, and returns scored findings with fix SQL that is never executed.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

Enables LLM agents to access Global Database's company intelligence, including company profiles, financials, ownership, people search, prospecting, and KYB/compliance lookups against official registries.

A small MCP server that lets an LLM query PostgreSQL, MySQL, MariaDB, SQL Server, or SQLite databases safely — read-only, role-restricted, and with sensitive data blacked out.

Enables LLM clients to safely inspect database schemas and run only approved read-only queries and stored procedures, with auditing.

Enables AI agents to turn raw calldata, transaction objects, JSON-RPC requests, EIP-712 typed data and personal_sign messages into short plain-English briefings covering what a request asks for, which risky allowances or permissions need attention, and what could not be verified. Runs entirely offline with no RPC, wallet, API key or safety verdict, using three read-only tools exposed to any MCP client.

Enables AI clients to safely query PostgreSQL or SQLite databases read-only through AST-validated guardrails, schema introspection, and statistical table profiling. It returns results as Markdown tables, JSON audit reports, and database health checks.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

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

A secure email gateway MCP server that protects AI agents from prompt injection attacks by scanning emails for malicious instructions before they reach the agent.

Enables AI assistants and signed-in support staff to search and read customer tickets, add internal notes, issue refunds under per-scope and per-customer limits, and export ticket data over a remote, OAuth-protected Streamable HTTP endpoint. Tool lists, resources, prompts, and write operations are gated by bearer tokens and audience-bound scopes so that refund and export actions stay bounded.

Enables account-isolated, read-only access to a chosen Gmail account for searching mail, retrieving message and thread content, downloading attachments, and listing labels. It verifies the actual Google OAuth grant and account before starting and emits ready-to-use Codex or JSON MCP client configuration.

Enables agents to run SELECT-only queries and inspect table metadata against configured databases via MCP Proxy, with timeouts, row and byte caps, and audit logging.

DataNexa is a local, read-only database MCP gateway for AI agents. It routes SQLite, MySQL, PostgreSQL, and any JDBC-compatible database through a single localhost endpoint, enforces read-only access via SQL AST validation with row, time, and connection limits, and keeps a local audit trail of every query.

Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging.

Enables an agent to read Slack channel history, threads, channel metadata and user info, and to search messages using your own account's browser session rather than a bot, with all access restricted to an explicit channel allowlist. Message sending, editing and deleting are deliberately not supported.

Enables database querying and modification through an MCP server where each action is gated by human-granted scopes, per-call confirmations for destructive operations, and revocable access.

Enables named, authenticated callers to run read-only introspection of a Google Cloud project and to read and write per-tenant notes that stay isolated between callers. Every request is scope-checked against a reviewed policy, rate-limited per caller, and audited without ever logging argument values.

Enables AI agents to interact with a user management REST API, providing list, get, and create operations while preventing destructive actions like update/delete through an explicit access registry.

A pre-action risk gate for AI agents. Your agent calls the forecast tool before any irreversible action — send email, run SQL, make a payment, delete a file — and gets a risk score (0–100) and a GO / CONFIRM / STOP verdict in a few seconds.

Enables AI agents to query PostgreSQL databases securely with read-only defaults, PII masking, rate limiting, and human-approved, expiring mutation tokens.

Enables secure remote SSH command execution with strict read-only enforcement, allowing safe delegation of SSH access to Claude while preventing write operations. Supports connection pooling, command validation, and comprehensive logging for audit trails.

Enables MCP clients to safely inspect and query an explicitly allowlisted subset of a Postgres database through four read-only tools: a readiness check, table listing, column description, and typed row selection with filters, ordering, and paging. It runs over stdio for local clients or Streamable HTTP for separately managed ones, with bound parameters, bounded reads, and read-only transactions.

Enables AES-256-CBC encryption and decryption of messages with passphrase-derived keys, exposing tools, resources, and prompts for MCP clients like VS Code Copilot Chat.

Provides agent certification and trust verification tools for AI agents, enabling certification checks, trust score calculations, audit ticket issuance, and emergency kill switch activation through the A-SOC trust network.