MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
A secure database access gateway for AI Agents: Empowering LLM (Agents) with database access capabilities.
MIT ★ 6 -
warp-sql-server-mcpstale
Secure MCP server for connecting Warp to SQL Server with graduated safety levels and comprehensive database operations
npm MIT -
sqlguard-mcpgithub.com/sealca/sqlguard-mcpupdated this year
Safety layer MCP server that intercepts SQL queries and enforces guardrails before they reach your database
npm MIT -
mcp-sql-analystgithub.com/sheeryn123/mcp-sql-analystupdated this year
Python MCP server for NL-to-SQL with safety and charts
-
Read-only SQL MCP server for PostgreSQL and SQL Server with schema introspection and safety guards for AI assistants.
-
sql-talkupdated this year
SQL Talk - 自然言語をSQLに変換するMCPサーバー(安全性保護・SSHトンネル対応) / SQL Talk - MCP Server for Natural Language to SQL conversion with safety guards and SSH tunnel support
npm MIT -
mcp-azure-sqlgithub.com/albahubio/mcp-azure-sqlupdated this year
Enterprise-grade MCP server for Azure SQL with Azure AD auth, 34 tools, tiered safety gates, and multi-agent support
npm MIT ★ 2 -
Text2SQL data-analysis agent: three handwritten LangGraph orchestrations (deterministic pipeline / autonomous ReAct loop / Supervisor multi-agent with LLM-as-Judge), 4-layer SQL safety, MCP server+client, human-in-the-loop write path with transactional dry-run. 60-case gold benchmark.
MIT -
@ryan4u/redash-mcp-serveractive
MCP server for Redash analytics integration - with SQL safety guard, caching and more
npm MIT -
txt-to-sqlgithub.com/pavani-aiml-space/txt-to-sqlupdated this year
A natural-language-to-SQL agent over Postgres/Supabase that translates plain-English questions into validated SQL and self-corrects on failure, with a rule-based fallback, safety policy layer, benchmark suite, and MCP server.
-
sql-explorer-mcpgithub.com/pawansingh3889/sql-explorer-mcpupdated this year
Read-only Model Context Protocol server for SQL databases. Lets LLMs (Claude, Cursor, ChatGPT, Continue) introspect and query SQL Server, Postgres, and SQLite with multi-layer safety guards including sql-sop linting.
pypi MIT -
Secure SQL proxy for AI agents — AST safety, per-agent RLS, audit log, MCP-native.
pypi MIT ★ 1 -
bi-gateway-mcpgithub.com/Riccowil/bi-gateway-mcpupdated this year
MCP server fronting SQL, Power BI Desktop & Fabric behind one gateway — two-layer SQL safety, adversarially tested.
Apache-2.0 -
discord-text2sql-mcpgithub.com/JstnClmnt/discord-text2sql-mcpupdated this year
Experimental MCP-native Text2SQL Discord assistant with schema grounding, layered SQL safety, charts, and reproducible evaluation.
MIT -
MCP Server for SQL Server database operations with comprehensive CRUD functionality, views, stored procedures, execution plan analysis, and safety features
npm MIT -
mcp-oracle-databasegithub.com/zademy/mcp-oracle-databaseupdated this year
MCP server for Oracle Database. Introspect schemas, run SQL/DML, call PL/SQL, and diagnose performance over STDIO — with safety enforced by Oracle's least-privilege model.
MIT ★ 3 -
Natural-language SQL query server built on the Model Context Protocol (MCP) with dynamic DB configs, SQL-safety checks, and a Gradio web UI.
★ 1 -
mysql-mcp-xgithub.com/lr-liang/mysql-mcp-xupdated this year
MySQL MCP Server for Claude Desktop, Cursor and AI assistants. Supports MySQL 8+ with built-in SQL safety protection.
npm MIT -
A safety net for SQL Server stored procedures: capture what a procedure does today and verify that changes by humans or AI agents don't break it. CLI, MCP server and GitHub Action.
pypi MIT ★ 1 -
MariaDB-Guard-RO-MCPgithub.com/PmaControl/MariaDB-Guard-RO-MCPupdated this year
Production-ready read-only MCP server for MariaDB with built-in query safety guards, execution limits, and explainable SQL diagnostics.
GPL-3.0 ★ 1 -
General-purpose read-only MySQL MCP server with a SQL safety layer and structured results.
pypi Apache-2.0 -
mssql-mcpo-servergithub.com/mortada7-11/mssql-mcpo-serverupdated this year
A self-contained Model Context Protocol (MCP) server that exposes SQL Server metadata and read-only query execution as a structured HTTP API. It is designed to be consumed by AI orchestration layers (e.g. LangGraph, custom agents) that need reliable, safety-gated access to a SQL Server database.
★ 1 -
mcp-clickhousegithub.com/TopWent/mcp-clickhouseupdated this year
Model Context Protocol server exposing ClickHouse to LLM clients over stdio. Read-only by default, comment-aware SQL safety validator, five tools, distroless image.
MIT -
Production-style MCP server (Python/FastMCP): 8 typed tools for GitHub, Postgres, deploy status, and sandboxed filesystem — with SQL/path safety gates, dry-run writes, Docker, and CI.
-
Local MCP server that lets Claude inspect and diagnose PostgreSQL and SQL Server databases: schema, undeclared foreign keys, indexes, GDPR exposure, cascades, migration safety and query plans. Read-only; returns no row data by default.
nuget MIT -
mcp-data-analystgithub.com/flashgari/mcp-data-analystupdated this year
Natural-language data analyst: Claude answers questions by calling tools over a real MCP server (including a real subprocess/stdio test), with a read-only SQL safety guard and a FastAPI + Chart.js dashboard. 57 tests against real infrastructure.
MIT -
Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Two drop-in MCP servers (MySQL, SSH logs) keep safety red lines in code: read-only by default, dangerous SQL/shell blocked, production disabled, no stored credentials. A recommended Skill layer teaches the model when and how to use them.
MIT ★ 3 -
AI 에이전트를 위한 읽기 전용 SQL
MIT ★ 1 -
.NET SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.
nuget Apache-2.0 ★ 11 -
sql-sop-mcpgithub.com/pawansingh3889/sql-sop-mcpupdated this year
Model Context Protocol server that exposes sql-sop's SQL linter to LLMs (Claude, Cursor, ChatGPT, Continue).
pypi MIT -
SQL MCP server with risk classification, two-phase DANGER confirmation, and tamper-evident audit — built for safe AI database access
MIT -
Offline-first SQL audit engine and MCP SQL audit server for MySQL, TiDB, and PostgreSQL DDL/DML changes.
npm Apache-2.0 ★ 3 -
sqlgategithub.com/asd3358123/sqlgateupdated this year
A deterministic, fail-closed write gate for LLM-generated SQL, exposed over MCP. The model can't talk its way past it.
MIT -
A guarded MCP server that lets Claude query a MySQL database safely: single SELECT only, allowlisted columns, row limits, prompt-injection tests and measured results.
-
mcp-inject-bendergithub.com/jaspertvdm/mcp-inject-benderupdated this year
🎭 Inject Bender - Security Through Absurdity! Transform SQL injections into hiking boot ads. Skippie 📎 & Odin ⚡
pypi NOASSERTION -
Read-only, audited MCP server that gives AI agents safe access to SQL warehouses: AST-checked SQL, database-enforced read-only, timeouts, PII masking
MIT -
MCP server that gives AI agents a compact map of a database schema, finds join paths between tables, and validates SQL through an AST-based read-only guard (sqlglot).
MIT -
A Model Context Protocol server that lets AI assistants explore and query a PostgreSQL or SQLite database read-only, behind a SQL allow-list, automatic row limits, timeouts, column masking, rate limits and a JSONL audit log.
MIT -
Let an AI agent write to Postgres one statement at a time: dry-run first, current-value checks, row cap enforced in the transaction, masked snapshots. CLI + MCP server, no dependencies.
MIT -
vektor-guardactive
Stop your AI agent from running DROP TABLE on production. Decides on PostgreSQL's own parse tree, not patterns. MCP server for Claude Desktop and Cursor, plus a CLI.
npm MIT -
BLACK_WALL MCP server — a pre-action risk check your AI agent calls before any irreversible action (send email, move money, run SQL, delete data).
npm MIT -
An MCP server that lets an LLM agent query a real database and refuses anything it cannot prove is a read. Writes require out-of-band human approval bound to the exact statement. Go.
MIT -
@porcorosso0709/database-safeupdated this year
Safety-oriented MCP database server: same tools as database-mcp fork, without exposing delete-connection; use DB grants for read/write policy
npm MIT -
Project-Heimdallgithub.com/AnubhavMadhav/Project-Heimdallupdated this year
A high-security Model Context Protocol (MCP) server for PostgreSQL. Acts as a read-only gatekeeper for LLMs by using AST parsing to strictly enforce safety and prevent data mutation.
MIT -
mcp-postgresgithub.com/aparcero/mcp-postgresupdated this year
MCP server for controlled PostgreSQL access: inspection, read-only queries, guarded DML, and admin operations with parser-backed safety policies.
go MIT -
Read-only MCP server that lets Claude analyse e-commerce orders safely: guarded SQL, PII masking, audit log, tested over stdio.
MIT -
Read-only MCP server over the Toronto open data warehouse: curated tools plus sqlglot-checked SQL, a least-privilege role and read-only transactions, tested end to end over MCP
MIT -
Rehearse anything before your AI agent does it. MCP server + CLI that shows the consequences of risky actions (SQL, shell, git, Terraform, cloud, SaaS) and returns safe / confirm / block.
npm Apache-2.0 -
PGAutoPilot is a production-ready PostgreSQL MCP server that lets any AI assistant safely interact with PostgreSQL using natural language. It combines schema-aware query generation, enterprise safety controls, and a minimal-configuration setup into a single executable.
npm ★ 2 -
Catch dangerous PostgreSQL migrations and slow queries before your AI agent ships them — offline, no DB credentials, never executes SQL. MCP server for Claude Code, Cursor, GitHub Copilot.
npm MIT -
Limetry is open-source agent action governance: check tool intents against policy before irreversible runs. Returns allow, deny, or approval_required with signed receipts and privacy-safe audit. TypeScript SDK, CLI, and MCP for IDE like Cursor, VS Code, GitHub Copilot, Claude. Optional CI, SQL, and Shopify adapters. MIT — self-host your own node.
npm MIT ★ 1