Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Provides programmatic access to Tiger Cloud services, databases, and documentation.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
TIGER_PUBLIC_KEY, TIGER_SECRET_KEY「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"tiger-cli": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"TIGER_PUBLIC_KEY",
"-e",
"TIGER_SECRET_KEY",
"ghcr.io/timescale/tiger-cli:0.27.0"
],
"env": {
"TIGER_PUBLIC_KEY": "your-value",
"TIGER_SECRET_KEY": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add tiger-cli --env TIGER_PUBLIC_KEY=your-value --env TIGER_SECRET_KEY=your-value -- docker run -i --rm -e TIGER_PUBLIC_KEY -e TIGER_SECRET_KEY ghcr.io/timescale/tiger-cli:0.27.0動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"tiger-cli": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"TIGER_PUBLIC_KEY",
"-e",
"TIGER_SECRET_KEY",
"ghcr.io/timescale/tiger-cli:0.27.0"
],
"env": {
"TIGER_PUBLIC_KEY": "your-value",
"TIGER_SECRET_KEY": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"tiger-cli": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"TIGER_PUBLIC_KEY",
"-e",
"TIGER_SECRET_KEY",
"ghcr.io/timescale/tiger-cli:0.27.0"
],
"env": {
"TIGER_PUBLIC_KEY": "your-value",
"TIGER_SECRET_KEY": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント timescale で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:TIGER_PUBLIC_KEY, TIGER_SECRET_KEY
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.27.0)がレジストリに届いたのは10 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにDockerも必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, LickityClick
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Create, edit and track LickityClick short links, campaigns and click stats from your AI assistant.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Tiger CLI is the command-line interface for Tiger Cloud. It provides commands for managing and querying database services, as well as an integrated Model Context Protocol (MCP) server for use with AI assistants.
Multiple installation methods are provided. Choose your preferred method from the options below. If you aren't sure, use the first one!
curl -fsSL https://cli.tigerdata.com | sh
irm https://cli.tigerdata.com/install.ps1 | iex
brew install --cask timescale/tap/tiger-cli
# Add repository
curl -s https://packagecloud.io/install/repositories/timescale/tiger-cli/script.deb.sh | sudo os=any dist=any bash
sudo apt-get install tiger-cli
For manual repository installation instructions, see here.
# Add repository
curl -s https://packagecloud.io/install/repositories/timescale/tiger-cli/script.rpm.sh | sudo os=rpm_any dist=rpm_any bash
sudo yum install tiger-cli
For manual repository installation instructions, see here.
go install github.com/timescale/tiger-cli/cmd/tiger@latest
To upgrade an existing installation to the latest release:
tiger upgrade
This downloads the latest published binary, verifies its checksum, and replaces the currently running binary in place. If Tiger CLI was installed via a package manager (Homebrew, apt, yum/dnf), tiger upgrade will instead point you at the matching package-manager command.
After installing Tiger CLI, authenticate with your Tiger Cloud account:
# Login to your Tiger account
tiger auth login
tiger --help
tiger service list
tiger service create --name my-database
tiger db uri
tiger db psql
tiger db query -c "SELECT now()"
tiger mcp install
tiger skills install
Tiger CLI provides the following commands:
tiger auth - Authentication managementlogin - Log in to your Tiger account (use --headless to authorize with a short code in a browser on any machine)logout - Log out from your Tiger accountstatus - Show current authentication status and project ID (alias: whoami)tiger project - Project managementlist - List all projects you have access to, marking the active one (alias: ls)use - Switch the active project (requires an OAuth login; clears the default service_id, since it belonged to the previous project) (alias: switch)tiger service - Service lifecycle management (aliases: services, svc)list - List all services (alias: ls)create - Create a new serviceget - Show detailed service information (aliases: describe, show)fork - Fork an existing servicestart - Start a stopped service (alias: resume)stop - Stop a running service (alias: pause)rename - Rename a serviceresize - Resize service CPU and memory allocationdelete - Delete a service (alias: rm)update-password - Update service master passwordlogs - View service logs (alias: log)metrics available - List the metric names available for a servicemetrics details - Show a metric's description, type, default aggregation and labelsmetrics series - Fetch a metric's time series, with label filters, an aggregation function, group by and bucket sizetiger db - Database operationspsql - Connect to a database with psql (in an interactive terminal, if the service has read replicas, offers to connect to one of them; use --no-replica-prompt to skip) (alias: connect)query - Execute a SQL query against a database and display the results, without needing psql (alias: sql)uri - Get connection URI for a service (alias: connection-string)ping - Test database connectivity (aliases: test, test-connection)schema - Display database schema information (tables, views, indexes, functions, TimescaleDB hypertables, and more)extensions list - List the PostgreSQL extensions installed in a database, with their versions and schemas (aliases: ext ls)save-password - Save a database password to configured password storage (keyring, pgpass, or none)create role - Create a new database role, with optional read-only enforcement, inherited grants (--from), and statement timeout (alias: create user)tiger config - Configuration management (alias: cfg)list - List current configuration (aliases: ls, show)set - Set configuration valueunset - Remove configuration value (aliases: rm, delete)reset - Reset configuration to defaults (alias: clear)tiger mcp - MCP server setup and managementinstall - Install and configure MCP server for an AI assistant (alias: add)start - Start the MCP serverlist - List available MCP tools, prompts, and resources (alias: ls)get - Get detailed information about a specific MCP capability (aliases: describe, show)tiger skills - Agent skills for AI coding agentsinstall - Install PostgreSQL and TimescaleDB skills for AI coding agents (alias: add)tiger feedback - Submit feedback or a bug report to the Tiger Data team (pass the message as an argument or on stdin)tiger version - Show version informationtiger upgrade - Upgrade the Tiger CLI to the latest version (alias: update)Use tiger --help for detailed information about each command, or browse the generated CLI reference.
Anywhere a command takes a service as an argument, it takes either its ID (or a read replica set ID) or its name:
tiger db psql my-api-db
tiger service stop my-api-db
Names are matched exactly. A name that matches more than one service is refused; run tiger service list to find the ID you want. A default service (tiger config set service_id, --service-id, or TIGER_SERVICE_ID) must be an ID, and destructive commands still ask you to type the ID to confirm. The MCP tools take IDs only.
Tiger CLI includes a Model Context Protocol (MCP) server that enables AI assistants like Claude Code to interact with your Tiger Cloud infrastructure. The MCP server provides programmatic access to database services and operations.
Configure the MCP server for your AI assistant:
# Interactive installation (prompts for client selection)
tiger mcp install
tiger mcp install claude-code # Claude Code tiger mcp install codex # Codex tiger mcp install copilot # GitHub Copilot CLI tiger mcp install cursor # Cursor IDE tiger mcp install devin # Devin tiger mcp install gemini # Gemini CLI tiger mcp install vscode # VS Code
After installation, restart your AI assistant to activate the Tiger MCP server.
If your MCP client is not supported by tiger mcp install, follow the client's instructions for installing MCP servers. Use tiger mcp start as the command to start the MCP server. For example, many clients use a JSON file like the following:
{
"mcpServers": { "tiger": { "command": "tiger", "args": [ "mcp", "start" ] } } }
The above instructions install the MCP server using the stdio transport. If you need to use the Streamable HTTP transport instead, you can start the server with tiger mcp start http --port 8080 and install it into your client using http://localhost:8080 as the URL.
The MCP server exposes the following tools to AI assistants:
Service Management:
service_list - List all database services in your projectservice_get - Get detailed information about a specific serviceservice_create - Create new database services with configurable resourcesservice_fork - Fork an existing database service to create an independent copyservice_start - Start a stopped database serviceservice_stop - Stop a running database serviceservice_rename - Rename a database serviceservice_resize - Resize a database service by changing CPU and memory allocationservice_delete - Permanently delete a database service (asks you to confirm first if the service is tagged PROD)service_update_password - Set a new, randomly generated master password for a service (asks you to confirm first if the service is tagged PROD)service_logs - View logs for a database serviceService Metrics:
service_metrics_available - List the metric names available for a service (hardware usage, PostgreSQL settings and activity, PgBouncer pools, TimescaleDB internals)service_metrics_details - Show a metric's description, type, default aggregation and labelsservice_metrics_series - Fetch a metric's time series over a time window, with label filters, an aggregation function, group by and bucket sizeDatabase Operations:
db_query - Execute SQL queries against a database service, passed inline or as a path to a SQL file, with support for parameterized queries, custom timeouts, and connection poolingdb_schema - Display a service's database schema (tables, views, materialized views, enums, functions, procedures, indexes, triggers, and TimescaleDB hypertable/continuous aggregate metadata) as readable text for an agent's contextdb_extensions_list - List the PostgreSQL extensions installed in a service database, with each extension's version, schema, and descriptionFeedback:
feedback - Submit feedback or a bug report to the Tiger Data teamThe MCP server automatically uses your CLI authentication and configuration, so no additional setup is required beyond tiger auth login.
In addition to the service management tools listed above, the Tiger MCP server also proxies tools from a remote documentation MCP server. This feature provides AI assistants with semantic search capabilities for PostgreSQL, TimescaleDB, and Tiger Cloud documentation, as well as prompts/guides for various Tiger Cloud features.
The proxied documentation server (pg-aiguide) currently provides the following tools:
view_skill - Retrieve comprehensive guides for Postgres and TimescaleDB features and best practicessearch_docs - Search PostgreSQL and TimescaleDB documentation using natural language queriesThis proxy connection is enabled by default and requires no additional configuration.
To disable the documentation proxy:
tiger config set docs_mcp false
Tiger CLI can install curated PostgreSQL and TimescaleDB skills directly into your coding agents:
# Interactive installation (prompts for install locations)
tiger skills install
tiger skills install universal claude-code
Skills are installed for the current user. The universal location, ~/.agents/skills, is read by most coding agents (Cursor, Codex, Gemini CLI, VS Code, GitHub Copilot CLI, Devin). Claude Code, Kiro CLI, and Google Antigravity read their own skills directories, so they're separate locations (claude-code, kiro-cli, antigravity). Naming a client that reads ~/.agents/skills, such as cursor, selects universal. Use --skills-dir to install into a directory of
冒頭だけを表示しています。続きはリポジトリで読めます