"Giving Claude full access to SQL Server for free" matching MCP servers:

Self-hosted credential store and API proxy for AI agents. One Bearer token, all your services. Handles OAuth refresh, encrypted storage, audit logging, and per-agent permissioning.

A governed SQL gateway for untrusted AI agents, providing controlled access to PostgreSQL, MySQL, and OceanBase with RBAC, field ACLs, row policies, and cost controls.

An MCP server that lets Claude query a mock business SQL database in plain language through read-only tools, with server-side guardrails that enforce SELECT-only queries and block access to sensitive payment data.

Enables secure database operations on SQL Server instances through a three-tier safety system, supporting schema exploration, query execution, performance analysis, and data export with configurable security levels from read-only to full development access.

Scans code for exposed secrets, API keys, tokens, and credentials across 69 patterns covering cloud services, AI platforms, payment providers, authentication services, and databases.

Enables AI agents to interact with Nextcloud files only through human-approved, time-limited grants, with mandatory audit logging and no standing content access.

Enables AI agents to interact with Home Assistant through tiered, human-gated access: free reads and reversible comfort controls, while sensitive actions like locks, alarm, covers, and climate changes require per-operation human approval via Matrix.

Enables read-only comparison of Stripe active entitlements against an application's effective access snapshots, returning matched, mismatch, or unknown results for agent-driven diagnostics.

Enables AI agents to securely read from and interact with Matrix and Microsoft Teams chat under scoped, expiring, human-approved grants, with per-operation approval for sending and editing messages and no free access to room content.

Enables read-only querying and diagnostics for dual SQL Server 2019 instances with rate limiting and security controls, accessible via MCP tools over HTTP.

Enables secure remote MCP server connections using Cloudflare Access OAuth, with user-authenticated tools on Cloudflare Workers.

Enables remote MCP connections with Cloudflare Access OAuth, providing tools like add and generateImage with user-based access control.

A remote MCP server with built-in Access OAuth, enabling authenticated MCP connections via Cloudflare Access and conditional tool permissions.

Enables remote MCP server with OAuth authentication using Cloudflare Access, allowing users to connect via sign-in with an identity provider.

Enables remote MCP connections with Cloudflare Access OAuth authentication, providing tools like add and restricted image generation.

A remote MCP server with Cloudflare Access OAuth authentication, deployable to Cloudflare Workers, enabling secure connections from MCP clients with identity-based access control.

A Cloudflare Workers-based MCP server that enables secure remote connections using built-in OAuth authentication via Cloudflare Access. It provides identity-based access control for MCP tools and supports persistent state management through Durable Objects and SSE.

A community MCP server for Cisco Secure Access that exposes the Secure Access REST API to AI clients as a curated catalog of tools for Admin, Deployments, Investigate, Policies, and Reports.

Enables AI agents to query Postgres databases read-only over the Model Context Protocol through three narrow tools, validating every statement as a single SELECT with an enforced row limit before it reaches the database. Guards against destructive statements, banned functions, system catalogs, and runaway queries via AST parsing plus a SELECT-only Postgres role.

Enables LLMs to propose UPDATE/DELETE SQL that is run in a transaction, measured, and rolled back, requiring human approval before applying to prevent unauthorized changes.