Production Safe Mysql Mcp Server

Created By
turkeryildirima month ago
A Model Context Protocol (MCP) server that gives AI agents direct access to MySQL databases even on production environments.
Overview

What It Can Do

Data Query & Mutation

  • execute_query — Run SELECT, INSERT, UPDATE, or DELETE statements with parameterized query support (? placeholders)
  • execute_transaction — Execute multiple statements as an atomic batch; if any statement fails the entire transaction is automatically rolled back

Schema Management

  • create_table — Create a new table
  • alter_table — Add/drop columns, rename columns, add indexes, and more
  • drop_table — Drop a table (requires ALLOW_DESTRUCTIVE_DDL=true)
  • show_tables — List all tables in a database
  • describe_table — Show column structure of a table

Database Management

  • list_databases — List all user databases (system databases excluded)
  • create_database — Create a new database with optional charset and collation
  • drop_database — Drop a database (requires ALLOW_DESTRUCTIVE_DDL=true)

Introspection

  • ping — Check MySQL connection health
  • show_columns — Show detailed column information for a table
  • get_server_info — Return MySQL version, character set, and collation (read-only)

Multi-Database Support

Every tool accepts a database parameter. You can query different databases within the same session without any extra configuration.


What It Cannot Do

The following operations are permanently blocked by the security filter and cannot be bypassed under any circumstances:

CategoryBlocked Commands
MySQL settingsSET GLOBAL, SET @@global.*, SET @@SESSION.sql_mode
User managementCREATE USER, DROP USER, ALTER USER, RENAME USER
Privilege managementGRANT, REVOKE
System commandsFLUSH, KILL, SHUTDOWN
ReplicationRESET MASTER/REPLICA, START/STOP SLAVE/REPLICA, CHANGE MASTER
File accessLOAD DATA INFILE, SELECT INTO OUTFILE/DUMPFILE
PluginsINSTALL PLUGIN, UNINSTALL PLUGIN

Additional constraints:

  • Multiple statements separated by ; in a single call are not allowed — use execute_transaction instead
  • drop_table and drop_database are disabled by default and will return an error unless ALLOW_DESTRUCTIVE_DDL=true is set
  • Query results are capped at MAX_ROWS rows (default: 1000); add a LIMIT clause for large tables

Server Config

{
  "mcpServers": {
    "mysql": {
      "command": "node",
      "args": [
        "/absolute/path/to/mysql-mcp/dist/index.js"
      ],
      "env": {
        "MYSQL_HOST": "localhost",
        "MYSQL_PORT": "3306",
        "MYSQL_USER": "mcp_user",
        "MYSQL_PASSWORD": "your_password",
        "MYSQL_DATABASE": "",
        "MAX_ROWS": "1000",
        "ALLOW_DESTRUCTIVE_DDL": "false"
      }
    }
  }
}
Project Info
Created At
a month ago
Updated At
a month ago
Author Name
turkeryildirim
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

16 hours ago