sequel-mcp

Name: sequel-mcp
Author: xicv

security MCP Server

MCP server: Claude talks to MySQL/MariaDB via Sequel Ace's saved connections. Policy-gated read/write/DDL/admin action sets, macOS Keychain credential storage, SSH tunnels, optional Touch ID.

byxicv

VerifiedInstall Ready

securitysecurity mysql

3 views0 stars0 forksv0.9.0MIT

View on GitHub Homepage Docs

Why This Matters

Discovered via github-topic:model-context-protocol and last synced 3mo ago.

VerifiedInstall Ready

Source: github-topic:model-context-protocol
Stars: 0
Last synced: 3mo ago
Install: Instructions detected

Install

1. Install the package

npx -y sequel-mcp

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "sequel-mcp": {
      "command": "npx",
      "args": [
        "sequel-mcp"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

Tools

Resources

Prompts

Standard I/O

Transport

Available Tools (51)

ddl

admin

dev

allow

describe_table

readOnly

restore_backup

destructive

local-dev

dev

INSERT

Post-mutation hint: `{kind:'range', start, end}` (auto-inc) or `{kind:'explicit', values}`

Tool

If Sequel Ace missing

audit_search

readOnly

prod-readonly

read-only

UPDATE

MySQL/MariaDB: `SELECT * FROM <table> WHERE <where> FOR UPDATE`; SQLite: pre-image `SELECT` inside `BEGIN IMMEDIATE`

confirm

read-only

allow

tamperEvidentChain

false

write

`INSERT`, `UPDATE`, `DELETE`, `REPLACE`

10s

off

execute

destructive

list_backups

readOnly

staging

dev

REPLACE

MySQL/MariaDB: `SELECT * FROM <table> WHERE id IN (<keys>) FOR UPDATE`; SQLite: same pre-image without `FOR UPDATE`

import_from_sequel_ace

"Favorites.plist not found" — use `add_connection` or `add_sqlite_connection` instead

txCtrl

`BEGIN`, `COMMIT`, `ROLLBACK`, `SAVEPOINT`

30s

off

list_connections

readOnly

sequel_ace_history

"queryHistory.db not found" — use `audit_search` instead

Setting

Default

admin

allow

list_databases

readOnly

history_search

readOnly

timeout

Touch ID

60s

**on**

get_default_connection

readOnly

Connection

Baseline

Statement

Backup

redactSqlInLog

false

Preset

read

remove_connection

destructive

doctor

readOnly

backupMaxMB

1000 (hard cap)

list_database_policies

readOnly

Scope

Effect

Field

Notes

autoCleanupHours

24 (lazy on boot)

read

`SELECT`, `SHOW`, `DESCRIBE`, `EXPLAIN`, read-only SQLite `PRAGMA`

deny

query

readOnly

audit_cleanup

destructive

prod-admin

read-only, `requireTouchID=true`

DELETE

Same

allow

deny

TRUNCATE

MySQL/MariaDB: `SELECT *` (capped) + `SHOW CREATE TABLE`

1

salt

Works Well With - Skills

verify-authenticity

真实性验证技能。分析用户提供的信息、消息、图片或内容，判断其真实性和可信度，识别虚假信息、AI生成内容或伪造内容。

220 starsHas guide

detecting-container-escape-attempts

Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators

61 starsHas guide

implementing-kubernetes-pod-security-standards

Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+. PS

61 starsHas guide

implementing-ebpf-security-monitoring

Implements eBPF-based security monitoring using Cilium Tetragon for real-time process execution tracking, network connection observability, file access auditing, and runtime enforcement. Covers TracingPolicy CRD authoring with kprobe/tracepoint hooks, in-kernel filtering via matchArgs/matchBinaries selectors, JSON event export, and integration with SIEM pipelines. Use when building kernel-level runtime security observability for Linux hosts or Kubernetes clusters.

61 starsHas guide

Works Well With - Agents

Agent Governance Toolkit

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

6227 starscrewai

Onecli

Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.

3452 stars

Agentshield

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

896 stars

Ironcurtain

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

602 stars

sequel-mcp

Why This Matters

Install

Available Tools (51)

ddl

dev

describe_table

restore_backup

local-dev

INSERT

Tool

audit_search

prod-readonly

UPDATE

confirm

read-only

tamperEvidentChain

write

10s

execute

list_backups

staging

REPLACE

import_from_sequel_ace

txCtrl

30s

list_connections

sequel_ace_history

Setting

admin

list_databases

history_search

timeout

60s

get_default_connection

Connection

Statement

redactSqlInLog

Preset

remove_connection

doctor

backupMaxMB

list_database_policies

Scope

Field

autoCleanupHours

read

deny

query

audit_cleanup

prod-admin

DELETE

allow

TRUNCATE

1

Works Well With - Skills

verify-authenticity

detecting-container-escape-attempts

implementing-kubernetes-pod-security-standards

implementing-ebpf-security-monitoring

Works Well With - Agents

Agent Governance Toolkit

Onecli

Agentshield

Ironcurtain

Guides & Tutorials

absolute-audit: A Claude Skill for Security Audits, CVE Scanning, and Defensive Code Hardening

Claude Skill `token-scam-analysis`: A Deep On-Chain Scam & Rug Pull Analysis Guide

absolute-upgrade: A Claude Skill for Safe, Incremental Dependency Upgrades