Gigalixir & Turso & GitHub MCP Server

Gigalixir & Turso & GitHub MCP Server

A multi-service MCP server for Cloudflare Workers that enables managing Gigalixir apps, querying Turso databases, and handling GitHub repositories through natural language.

Category
访问服务器

README

Gigalixir & Turso & GitHub MCP Server

A ultra high-performance, multi-service Model Context Protocol (MCP) server built for deployment to Cloudflare Workers (or run as an ESM module anywhere). It includes pre-integrated support for managing Gigalixir apps, querying or executing transactions on Turso databases, and managing GitHub repositories, branches, actions, files, pull requests, and issues.


📦 The 5 Essential Files to Push to GitHub

To deploy this MCP server to Cloudflare Workers, you only need to push the following 5 files to your GitHub repository:

  1. 📄 src/worker.js — The unified single-file MCP core handler containing security checks, tool registry, pipeline executors, and normalized gateways.
  2. 📄 wrangler.toml — Cloudflare Workers configuration file declaring compatibility flags and custom environment variables.
  3. 📄 package.json — Dependency definitions and standard wrangler control scripts (npm run build, npm run deploy).
  4. 📄 README.md — This documentation file explaining usage and setup instructions.
  5. 📄 .gitignore — Basic configuration to prevent pushing sensitive files, .wrangler/ builds, or node_modules.

🚀 Setting Up & Deploying to Cloudflare Workers

1. Configure Secrets & Environment Variables

Make sure to prepare the following credentials (stored as Cloudflare Worker Secrets):

  • GIGALIXIR_EMAIL — Your registered Gigalixir account email.
  • GIGALIXIR_API_KEY — Your Gigalixir API Key (retrieved from Gigalixir CLI using gigalixir api_key:show).
  • TURSO_DB_URL — The URL of your Turso database (e.g. libsql://yourdb-slug.turso.io).
  • TURSO_AUTH_TOKEN — Your Turso database authorization bearer token.
  • GITHUB_TOKEN — A GitHub Personal Access Token (classic or Fine-grained) with access to your repositories and pull requests.

2. Install & Deploy

Clone your GitHub repository and build:

# Install dependencies
npm install

# Log in to Cloudflare
npx wrangler login

# Set environment secrets securely on Cloudflare
npx wrangler secret put GIGALIXIR_EMAIL
npx wrangler secret put GIGALIXIR_API_KEY
npx wrangler secret put TURSO_DB_URL
npx wrangler secret put TURSO_AUTH_TOKEN
npx wrangler secret put GITHUB_TOKEN

# Deploy directly to Cloudflare edge edge network!
npx wrangler deploy

🛠️ Integrated MCP Tools Breakdown

🔴 Gigalixir Management Tools

  • list_apps — Lists all Gigalixir apps in your account.
  • get_app — Gets details of a specific app.
  • get_configs & set_config & delete_config — Retrieve, set, or delete environmental configs safely (with resilient backoff to support both singular and plural endpoint variants).
  • get_replicas & scale — Read or scale your instance deployment replicas (scaling to 0 shuts down the instance).
  • list_releases & rollback — Read release versions or rollback instantly.
  • restart — Gracefully cycles app processes through standard sequence.
  • get_logs — High-performance chunk-streaming log reader capped to a hard 3-second limit to guarantee zero MCP gateway timeouts.

🔵 Turso Database Tools

  • turso_query — Execute read-only SQL SELECT queries with secure parameter parsing.
  • turso_execute — Execute state-changing SQL operations (INSERT, UPDATE, DELETE, CREATE, DROP).
  • turso_list_tables — List database master tables instantly.
  • turso_describe_table — Query columns, schema metadata, types, constraints, and indexes.
  • turso_transaction — Run multi-statement database transactions with integrated auto-rollback safety handlers if any query fails.

🟢 GitHub Workspace Tools

  • github_list_repos & github_get_repo — Query user repository definitions and specs.
  • github_create_repo — Create a new GitHub repository.
  • github_list_files & github_get_file — Recurse, tree-walk, or read raw contents.
  • github_create_file & github_update_file & github_delete_file — Create, update, or delete files securely with auto-resolved folder tree SHAs.
  • github_create_pr — Generate pull requests between head and base branch tracks.

🛡️ Production-Grade AI DevOps & Safety Controls (New)

The MCP server incorporates advanced guardrails, observability, and orchestration layers to transition from a collection of raw tools to a safe, self-healing AI DevOps Agent system:

⚙️ 1. Safety Guardrails & Access Rules

All state-changing operations are monitored by a local guardrail layer. Accidental or destructive acts are blocked unless explicit permission bypass is granted:

  • Outage Prevention: Scaling active deployment replicas pool size to 0 is blocked by default.
  • Secret Deletion Protection: Deleting configurations containing database strings, credentials, tokens, URLs, or security secrets is locked.
  • Database Guardrails: Destructive SQL commands (e.g., DROP TABLE, TRUNCATE) are blocked on custom executes.
  • Version Control Lock: Accidentally deleting core files from git via github_delete_file is locked.
  • How to Bypass: If you explicitly intend to execute a locked operation, pass the parameter "bypass_safety": true in the tool call.

🧪 2. Universal Dry-Run Simulator

Before executing any state-altering operations (scaling, deleting configs, commits, rollbacks, SQL mutations), pass "dry_run": true to preview the actions. The tool will return a detailed simulation explanation and log the trace without changing any remote resources.

📊 3. Real-Time Observability & Auditing

  • audit_traces_list — Retrieve real-time tracking logs of all executed actions, including timestamps, durations, statuses, targets, parameters (with sanitised pay-loads), and errors. Perfect for auditing AI operator behaviors.
  • get_system_safety_policies — Standard endpoint to query current safety postures, rule sets, limits, and dry-run instructions.

🚂 4. Core Orchestration Pipelines & Workflows

  • orchestrate_deploy_pipeline — Performs complete end-to-end git-to-cloud deployments (verifies packages on GitHub, sets Gigalixir environments, triggers rolling restarts, and parses container health logs).
  • diagnose_and_repair_app — Scans application runtimes, scales, and retrieves trailing log traces; detects crash loops or replicas drifts, and triggers self-healing cycles (e.g., scale recovery, graceful process recycles).

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选