
MySQL Ops MCP
io.github.GT-dinuoPublished by GitHub account GT-dinuov1.0.0Updated Oct 24, 2026
MySQL MCP server: browse schema, query, CRUD. Delete/drop gated by user approval.
Overview
Local MCP server that lets an AI assistant browse MySQL schemas, run SELECT queries and perform CRUD, with DELETE and DROP gated by user approval.
- What you can do
- List databases and tables, and describe table columns and types
- Inspect full table details including indexes, DDL and statistics
- Run SELECT queries against any database
- Create tables, insert and update rows, with per-tool SQL verb validation
- Delete rows or drop tables, each requiring explicit client-side approval
- Run arbitrary custom SQL through a general execute_sql tool
- When to use it
- Useful when you want an assistant to explore and modify a MySQL database in natural language from a desktop client such as Claude Code, Cursor or Codex, for example inspecting schemas, drafting queries or making small data changes.
- Requirements
- Runs locally over stdio via npx, so Node.js 18 or newer is needed. A reachable MySQL server plus credentials supplied through environment variables DB_HOST, DB_PORT, DB_USER, DB_PASSWORD and DB_DATABASE; all are optional and default to localhost, 3306, root and no default database.
Installation
In SourceWeft
- Open MySQL Ops MCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
MySQL Ops MCP
English | 简体中文
[npm version] [License: MIT] [Node.js] [MCP] [GitHub stars]
A MySQL database MCP Server. Let AI tools like Claude Code / Cursor / Codex talk to your MySQL databases in natural language — browse databases and tables, inspect schemas, run queries, and perform CRUD operations, with destructive operations (DELETE / DROP) gated behind explicit user approval.
Features
- 🗄️ Schema browsing: list databases, list tables, describe table structure, full table info (indexes, DDL, stats)
- 🔍 Queries: run
SELECTqueries against any database - ✏️ CRUD: create tables, insert, update — with SQL-statement validation per tool
- 🔐 Approval-gated destructive ops:
delete_dataanddrop_tablealways require explicit user confirmation in the client - 🔌 Zero install: runs via
npx, configured entirely through environment variables
Installation
Requires Node.js 18+. No clone or build needed — npx fetches and runs the published npm package on first use (see the config below).
To build from source instead (e.g. for development):
Build output goes to dist/; the entry point is dist/index.js.
Configuration
In each project where you want to use this tool, create (or append to) .mcp.json:
If you built from source, point the command at the local build instead: "command": "node", "args": ["/absolute/path/to/mysql-ops-mcp/dist/index.js"].
Environment Variables
Usage
Once configured, just ask in natural language in your AI tool:
Destructive operations (delete_data, drop_table) are always confirmed by the MCP client before execution — nothing irreversible happens silently.
Tool List
Security
- Destructive operations require approval:
delete_dataanddrop_tableare gated by the MCP client's tool-call confirmation — approve or reject each one. - Statement validation: each write tool only accepts its own SQL verb (e.g.
queryrejects anything butSELECT). - Use a least-privilege account: don't connect as
rootin production — create a MySQL user scoped to the databases the AI may touch. - Never commit credentials:
.env/.mcp.jsonwith real passwords must stay out of version control (.gitignorealready covers.env).
Testing the Connection
After configuring .env (copy from env.example), you can verify connectivity before wiring up the client:
Development
License
MIT © 2026 mysql-ops-mcp
Source: README.md at commit 295b862
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts