Supabaseデータベースとやり取りするためのモデルコンテキストプロトコル（MCP）サーバー。このサーバーは、MCPインターフェースを介してテーブルをクエリしたり、TypeScript型を生成したりするためのツールを提供します。
クエリ テーブル: 次のサポートを使用して任意のテーブルでクエリを実行します。
スキーマの選択
列フィルタリング
複数の演算子を含むWhere句
ページネーション
エラー処理
型生成: データベースの TypeScript 型を生成します。
あらゆるスキーマ (public、auth、api など) のサポート
ローカルとリモートの両方の Supabase プロジェクトで動作します
コンソールへの直接出力
自動プロジェクト参照検出
Related MCP server: SchemaFlow MCP Server
Node.js (v16 以上)
Supabase プロジェクト (ローカルまたはホスト)
Supabase CLI (型生成用)
リポジトリをクローンします。
git clone https://github.com/yourusername/supabase-mcp-server.git
cd supabase-mcp-server依存関係をインストールします:
npm installSupabase CLI をインストールします (型生成に必要)。
# Using npm
npm install -g supabase
# Or using Homebrew on macOS
brew install supabase/tap/supabaseSupabase の資格情報を取得します。
ホストされたプロジェクトの場合:
Supabaseプロジェクトダッシュボードに移動します
プロジェクト設定 > API に移動します
プロジェクト URL と service_role キー (anon キーではありません) をコピーします。
ローカルプロジェクトの場合:
ローカルのSupabaseインスタンスを起動する
ローカル URL を使用します (通常はhttp://localhost:54321 )
ローカルのservice_roleキーを使用する
環境変数を設定します。
# Create a .env file (this will be ignored by git)
echo "SUPABASE_URL=your_project_url
SUPABASE_KEY=your_service_role_key" > .envサーバーを構築します。
npm run buildClaude デスクトップの設定を開きます。
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
サーバー構成を追加します。
{
"mcpServers": {
"supabase": {
"command": "node",
"args": ["/absolute/path/to/supabase-mcp-server/build/index.js"],
"env": {
"SUPABASE_URL": "your_project_url",
"SUPABASE_KEY": "your_service_role_key"
}
}
}
}VSCode 設定を開きます。
macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
Windows: %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
Linux: ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
サーバー構成を追加します (Claude Desktop と同じ形式)。
// Query with schema selection and where clause
<use_mcp_tool>
<server_name>supabase</server_name>
<tool_name>query_table</tool_name>
<arguments>
{
"schema": "public",
"table": "users",
"select": "id,name,email",
"where": [
{
"column": "is_active",
"operator": "eq",
"value": true
}
]
}
</arguments>
</use_mcp_tool>// Generate types for public schema
<use_mcp_tool>
<server_name>supabase</server_name>
<tool_name>generate_types</tool_name>
<arguments>
{
"schema": "public"
}
</arguments>
</use_mcp_tool>スキーマ選択と where 句のサポートを使用して特定のテーブルをクエリします。
パラメータ:
schema (オプション): データベーススキーマ (デフォルトは public)
table （必須）: クエリするテーブルの名前
select （オプション）: カンマ区切りの列リスト
where (オプション): 次の条件の配列:
column : 列名
operator : eq、neq、gt、gte、lt、lte、like、ilike、is のいずれか
value : 比較する値
Supabase データベース スキーマの TypeScript 型を生成します。
パラメータ:
schema (オプション): データベーススキーマ (デフォルトは public)
Supabase CLI がインストールされていることを確認します。
supabase --versionローカルプロジェクトの場合:
ローカルのSupabaseインスタンスが実行中であることを確認してください
service_roleキーが正しいことを確認してください
ホストされたプロジェクトの場合:
プロジェクト参照が正しいことを確認してください（URL から抽出）
anonキーではなくservice_roleキーを使用していることを確認してください
スキーマとテーブル名を確認してください
SELECT句とWHERE句の列名を確認する
service_role キーに必要な権限があることを確認してください
リポジトリをフォークする
機能ブランチを作成します: git checkout -b feature/my-feature
変更をコミットします: git commit -am 'Add my feature'
ブランチにプッシュする: git push origin feature/my-feature
プルリクエストを送信する
MITライセンス - 詳細はLICENSEファイルを参照
Generate TypeScript types for your Supabase database schema
| Name | Required | Description | Default |
|---|---|---|---|
| schema | No | Database schema (optional, defaults to public) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does but doesn't describe how it works - whether it connects to a live database, reads from configuration files, requires authentication, has rate limits, or what format the output takes. The description is functional but lacks operational context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the core functionality without any wasted words. It's appropriately sized for a tool with one simple parameter and gets straight to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that presumably generates code/types from a database schema, the description is minimal. With no annotations and no output schema, it doesn't explain what the output looks like (TypeScript files? Inline code?), how errors are handled, or any dependencies or requirements. The description is functional but lacks important context for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the input schema already documents the single optional 'schema' parameter with its default value. The description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline expectation but doesn't provide additional value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Generate TypeScript types') and target resource ('your Supabase database schema'), providing a complete purpose statement. It distinguishes from the sibling tool 'query_table' which appears to be for data querying rather than schema type generation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, nor any context about prerequisites or constraints. While it's clear what the tool does, there's no information about appropriate use cases or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query a specific table with schema selection and where clause support
| Name | Required | Description | Default |
|---|---|---|---|
| schema | No | Database schema (optional, defaults to public) | |
| table | Yes | Name of the table to query | |
| select | No | Comma-separated list of columns to select (optional, defaults to *) | |
| where | No | Array of where conditions (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool queries a table but doesn't mention whether this is read-only (likely but not confirmed), what permissions are required, whether it supports pagination/limits, error handling, or what the output format looks like. The description adds minimal behavioral context beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the core functionality without unnecessary words. It's appropriately sized for the tool's complexity and front-loads the main purpose immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a database query tool with 4 parameters and no annotations or output schema, the description is insufficient. It doesn't address key contextual elements like: whether this is a safe read operation, what authentication/permissions are needed, how results are returned (format, size limits), error conditions, or relationship to the sibling tool. The 100% schema coverage helps with parameters but doesn't compensate for missing behavioral context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 4 parameters thoroughly. The description mentions 'schema selection and where clause support' which aligns with parameters in the schema but doesn't add meaningful semantic context beyond what's already in the parameter descriptions. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Query') and resource ('a specific table'), with additional functionality mentioned ('schema selection and where clause support'). It distinguishes from the sibling 'generate_types' by focusing on data retrieval rather than type generation. However, it doesn't specify if this is a read-only query or might modify data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description mentions functionality but doesn't indicate scenarios where this tool is appropriate, prerequisites for use, or limitations compared to other query methods. The sibling tool 'generate_types' serves a completely different purpose, so no comparative guidance is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0generate_typesquery_tableScored across 2 tools
The two tools have clearly distinct purposes: generate_types focuses on TypeScript type generation from the database schema, while query_table handles data retrieval from specific tables with filtering. There is no overlap or ambiguity between these functions.
Both tools follow a consistent verb_noun naming pattern (generate_types and query_table), using snake_case throughout. The naming is predictable and readable without any deviations.
With only 2 tools, the server feels under-scoped for a Supabase integration, which typically involves operations like create, update, delete, and schema management beyond just querying and type generation. This limited set may hinder agent workflows.
The server lacks essential CRUD operations (e.g., insert, update, delete) and other Supabase features like authentication or real-time subscriptions, making it severely incomplete for typical database interactions. Agents will face significant gaps in functionality.
Your Supabase account in natural language: run SQL, apply migrations, manage tables, storage, edge f
Manage Supabase projects end to end across database, auth, storage, realtime, and migrations. Moni…
MCP server for interacting with the Supabase platform
Query Postgres, MySQL, SQL Server, Oracle, BigQuery, ClickHouse and Redshift from your AI client.
