de en es ja ko ru zh

mcp-turso-cloud

Name: mcp-turso-cloud
Author: spences10

by spences10

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

mcp-turso-cloud

LLM向けにTursoデータベースとの統合を提供する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、組織レベルとデータベースレベルの両方の操作を処理する2段階認証システムを実装しており、LLMからTursoデータベースを直接管理およびクエリすることを容易にします。

特徴

🏢 組織レベルの運用

データベースの一覧表示: Turso 組織内のすべてのデータベースを表示します
データベースの作成: カスタマイズ可能なオプションを使用して新しいデータベースを作成します
データベースの削除: 組織からデータベースを削除します
データベーストークンの生成: 特定のデータベースの認証トークンを作成する

💾 データベースレベルの操作

テーブルの一覧表示: 特定のデータベース内のすべてのテーブルを表示します
読み取り専用クエリの実行: SELECT および PRAGMA クエリ (読み取り専用操作) を実行します。
クエリの実行: 潜在的に破壊的な SQL クエリ (INSERT、UPDATE、DELETE など) を実行します。
テーブルの説明: データベーステーブルのスキーマ情報を取得します
ベクトル検索: SQLite ベクトル拡張機能を使用してベクトル類似性検索を実行します

Related MCP server: Supabase MCP Server

⚠️ 重要: クエリ実行のセキュリティ ⚠️

このサーバーは、セキュリティを重視して、読み取り専用と破壊的なデータベース操作を分離します。

SELECT および PRAGMA クエリにはexecute_read_only_query使用します (安全な読み取り専用操作)
INSERT、UPDATE、DELETE、CREATE、DROP、およびデータを変更するその他の操作にはexecute_query使用します。

この分離により、異なる権限レベルと承認要件が可能になります。

読み取り専用操作は多くのコンテキストで自動承認できます
破壊的な操作には安全のための明示的な承認が必要になる場合があります

**SQLクエリを承認する前に、必ず注意深く読み、確認してください。**これは、データを変更または削除する可能性のある破壊的な操作の場合に特に重要です。各クエリの実行を許可する前に、そのクエリが何を行うのかをよく理解してください。

2段階認証システム

サーバーは高度な認証システムを実装しています。

組織レベルの認証
- Turso Platform APIトークンを使用する
- データベースと組織レベルの運用を管理します
- Tursoダッシュボードから取得
データベースレベルの認証
- データベース固有のトークンを使用する
- 組織トークンを使用して自動的に生成されます
- パフォーマンスのためにキャッシュされ、必要に応じてローテーションされます

構成

このサーバーはMCPクライアント経由で設定する必要があります。以下に、様々な環境における設定例を示します。

Cline/Claude デスクトップ構成

Cline/Claude Desktop MCP 設定に以下を追加します:

{
	"mcpServers": {
		"mcp-turso-cloud": {
			"command": "npx",
			"args": ["-y", "mcp-turso-cloud"],
			"env": {
				"TURSO_API_TOKEN": "your-turso-api-token",
				"TURSO_ORGANIZATION": "your-organization-name",
				"TURSO_DEFAULT_DATABASE": "optional-default-database"
			}
		}
	}
}

WSL 構成の Claude デスクトップ

WSL 環境の場合は、Claude Desktop 構成に以下を追加します。

{
	"mcpServers": {
		"mcp-turso-cloud": {
			"command": "wsl.exe",
			"args": [
				"bash",
				"-c",
				"TURSO_API_TOKEN=your-token TURSO_ORGANIZATION=your-org node /path/to/mcp-turso-cloud/dist/index.js"
			]
		}
	}
}

環境変数

サーバーには次の環境変数が必要です。

TURSO_API_TOKEN : Turso プラットフォーム API トークン (必須)
TURSO_ORGANIZATION : Turso組織名（必須）
TURSO_DEFAULT_DATABASE : 何も指定されていない場合に使用するデフォルトのデータベース（オプション）
TOKEN_EXPIRATION : 生成されたデータベーストークンの有効期限（オプション、デフォルト: '7d'）
TOKEN_PERMISSION : 生成されたトークンの権限レベル（オプション、デフォルト: 'full-access'）

API

サーバーは、カテゴリ別に整理された MCP ツールを実装します。

整理ツール

データベース一覧

Turso 組織内のすべてのデータベースを一覧表示します。

パラメータ: なし

応答例:

{
	"databases": [
		{
			"name": "customer_db",
			"id": "abc123",
			"region": "us-east",
			"created_at": "2023-01-15T12:00:00Z"
		},
		{
			"name": "product_db",
			"id": "def456",
			"region": "eu-west",
			"created_at": "2023-02-20T15:30:00Z"
		}
	]
}

データベースの作成

組織内に新しいデータベースを作成します。

パラメータ:

name (文字列、必須): 新しいデータベースの名前
group (文字列、オプション): データベースを割り当てるグループ
regions （文字列[]、オプション）：データベースを展開するリージョン

例：

{
	"name": "analytics_db",
	"group": "production",
	"regions": ["us-east", "eu-west"]
}

データベースの削除

組織からデータベースを削除します。

パラメータ:

name (文字列、必須): 削除するデータベースの名前

例：

{
	"name": "test_db"
}

データベーストークンを生成する

特定のデータベースの新しいトークンを生成します。

パラメータ:

database (文字列、必須): データベース名
expiration （文字列、オプション）: トークンの有効期限
permission (文字列、オプション): 権限レベル ('full-access' または 'read-only')

例：

{
	"database": "customer_db",
	"expiration": "30d",
	"permission": "read-only"
}

データベースツール

リストテーブル

データベース内のすべてのテーブルを一覧表示します。

パラメータ:

database (文字列、オプション): データベース名 (指定されていない場合はコンテキストを使用)

例：

{
	"database": "customer_db"
}

読み取り専用クエリの実行

データベースに対して読み取り専用の SQL クエリ (SELECT、PRAGMA) を実行します。

パラメータ:

query (文字列、必須): 実行するSQLクエリ（SELECTまたはPRAGMAである必要があります）
params (オブジェクト、オプション): クエリパラメータ
database (文字列、オプション): データベース名 (指定されていない場合はコンテキストを使用)

例：

{
	"query": "SELECT * FROM users WHERE age > ?",
	"params": { "1": 21 },
	"database": "customer_db"
}

クエリ実行

データベースに対して潜在的に破壊的な SQL クエリ (INSERT、UPDATE、DELETE、CREATE など) を実行します。

パラメータ:

query (文字列、必須): 実行するSQLクエリ（SELECTまたはPRAGMAは使用できません）
params (オブジェクト、オプション): クエリパラメータ
database (文字列、オプション): データベース名 (指定されていない場合はコンテキストを使用)

例：

{
	"query": "INSERT INTO users (name, age) VALUES (?, ?)",
	"params": { "1": "Alice", "2": 30 },
	"database": "customer_db"
}

テーブルの説明

テーブルのスキーマ情報を取得します。

パラメータ:

table （文字列、必須）: テーブル名
database (文字列、オプション): データベース名 (指定されていない場合はコンテキストを使用)

例：

{
	"table": "users",
	"database": "customer_db"
}

ベクター検索

SQLite ベクター拡張機能を使用してベクター類似性検索を実行します。

パラメータ:

table （文字列、必須）: テーブル名
vector_column （文字列、必須）: ベクトルを含む列
query_vector (number[], 必須): 類似検索のクエリベクトル
limit (数値、オプション): 結果の最大数 (デフォルト: 10)
database (文字列、オプション): データベース名 (指定されていない場合はコンテキストを使用)

例：

{
	"table": "embeddings",
	"vector_column": "embedding",
	"query_vector": [0.1, 0.2, 0.3, 0.4],
	"limit": 5,
	"database": "vector_db"
}

発達

設定

リポジトリをクローンする
依存関係をインストールします:

npm install

プロジェクトをビルドします。

npm run build

開発モードで実行:

npm run dev

出版

package.json のバージョンを更新する
プロジェクトをビルドします。

npm run build

npm に公開:

npm publish

トラブルシューティング

APIトークンの問題

認証エラーが発生した場合:

Turso APIトークンが有効であり、必要な権限があることを確認してください
組織名が正しいことを確認してください
トークンの有効期限が切れていないことを確認してください

データベース接続の問題

データベースへの接続に問題がある場合:

組織内にデータベースが存在することを確認する
APIトークンがデータベースにアクセスできることを確認してください
データベース名が正しいことを確認してください

貢献

貢献を歓迎します！お気軽にプルリクエストを送信してください。

ライセンス

MIT ライセンス - 詳細についてはLICENSEファイルを参照してください。

謝辞

構築されたもの:

Available Tools

9 tools

create_database✓ SAFE: Create a new database in your Turso organization. Database name must be unique.C

✓ SAFE: Create a new database in your Turso organization. Database name must be unique.

Name	Required	Description
`name`	Yes	Name of the database to create - Must be unique within organization
`group`	No	Optional group name for the database (defaults to "default")
`regions`	No	Optional list of regions to deploy the database to (affects latency and compliance)

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions 'SAFE' but does not explain any behavioral traits such as mutability, error handling, permissions, or idempotency. The unique name constraint is the only behavioral hint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with a single sentence that conveys the core purpose. However, it is identical to the title, which could be seen as redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, no annotations, and 3 parameters, the description should provide more context about return values or side effects. It does not address what happens after creation or any error conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so baseline is 3. The description adds the unique name constraint, which is already in the schema description. No additional context is provided for 'group' or 'regions' parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 does it mention prerequisites or when not to use it. It simply states what it does.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

delete_database⚠️ DESTRUCTIVE: Permanently deletes a database and ALL its data. Cannot be undone. Always confirm with user before proceeding and verify correct database name.B

⚠️ DESTRUCTIVE: Permanently deletes a database and ALL its data. Cannot be undone. Always confirm with user before proceeding and verify correct database name.

Name	Required	Description	Default
`name`	Yes	Name of the database to permanently delete - WARNING: ALL DATA WILL BE LOST FOREVER

TDQS

B3.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It explicitly states the destructive and irreversible nature: 'Permanently deletes' and 'Cannot be undone.' This sufficiently discloses the critical behavior, though it omits details like permissions or error handling. The warning about confirmation adds transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is repeated from the title, which is concise but slightly redundant. It is front-loaded with a warning. While efficient, it could be more structured (e.g., separate into purpose and caution). Loses a point for repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should clarify what the tool returns (e.g., success confirmation). It lacks details on return value, error states, or post-deletion effects. For a destructive tool with a simple interface, it is moderately complete but could be improved.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%. The parameter description 'Name of the database to permanently delete - WARNING: ALL DATA WILL BE LOST FOREVER' adds emphasis but does not provide additional semantic meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a strong usage guideline: 'Always confirm with user before proceeding and verify correct database name.' This directs the agent to take caution but does not explicitly state when to avoid using the tool or mention alternatives. The context of sibling tools implies it is only for deletion, so the guideline is clear but not comprehensive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

describe_tableGets schema information for a tableC

Gets schema information for a table

Name	Required	Description	Default
`table`	Yes	Table name
`database`	No	Database name (optional, uses context if not provided)

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries the full burden of behavioral disclosure. It implies a read-only operation by using 'Gets', but it does not explicitly state that the tool is non-destructive, requires no special permissions, or has any side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with one verb and one phrase, making it very concise. It front-loads the purpose without extraneous information, though it could be slightly expanded to include behavioral details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema and annotations, the description should compensate by explaining what the schema information includes (e.g., columns, types, constraints). It does not, leaving the agent to guess the return format, which is inadequate for effective tool selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of parameters with descriptions, so the schema provides the necessary meaning. The description adds no extra information about parameters beyond what is already in the schema, which meets the baseline for this dimension.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 does it mention prerequisites or exclusions. It only states what the tool does, leaving the agent to infer usage context from the tool name and sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execute_query⚠️ DESTRUCTIVE: Execute SQL that can modify/delete data (INSERT, UPDATE, DELETE, DROP, ALTER). Always confirm with user before destructive operations.C

⚠️ DESTRUCTIVE: Execute SQL that can modify/delete data (INSERT, UPDATE, DELETE, DROP, ALTER). Always confirm with user before destructive operations.

Name	Required	Description
`query`	Yes	SQL query to execute
`params`	No	Query parameters (optional) - Use parameterized queries for security
`database`	No	Database name (optional, uses context if not provided)

TDQS

C2.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that the tool is destructive and can modify/delete data, which is critical behavioral information. Without annotations, this is the primary disclosure, but it lacks further details on side effects, permissions, or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and gets to the point, but it is a verbatim repeat of the title, making it redundant. It is concise but not optimally structured as it wastes space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive SQL execution tool with no output schema and no annotations, the description is too sparse. It does not explain return values, error behavior, or execution context, leaving significant gaps for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage with clear descriptions for each parameter. The tool description does not add any parameter-specific meaning, so the schema handles this dimension adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions confirming with the user before destructive operations, which is a useful guideline. However, it does not explicitly differentiate from the sibling 'execute_read_only_query' or state when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execute_read_only_query✓ SAFE: Execute read-only SQL queries (SELECT, PRAGMA, EXPLAIN). Automatically rejects write operations.B

✓ SAFE: Execute read-only SQL queries (SELECT, PRAGMA, EXPLAIN). Automatically rejects write operations.

Name	Required	Description
`query`	Yes	Read-only SQL query to execute (SELECT, PRAGMA, EXPLAIN only)
`params`	No	Query parameters (optional) - Use parameterized queries for security
`database`	No	Database name (optional, uses context if not provided) - Specify target database

TDQS

B3.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the key behavioral trait of rejecting write operations, which is crucial for safety. No annotations are present, so the description carries the full burden. It does not cover error handling or performance.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, identical to the title, which is very concise. However, the repetition could be better utilized to add extra detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only query tool, the description adequately covers purpose and safety. Absence of output schema or annotation is mitigated by the clear statement of behavior, though error handling could be mentioned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed parameter descriptions. The tool description adds no additional meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear guidance to use this tool for read-only queries and highlights its automatic rejection of writes, but does not explicitly mention alternative tools or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

generate_database_tokenGenerate a new token for a specific databaseC

Generate a new token for a specific database

Name	Required	Description	Default
`database`	Yes	Name of the database to generate a token for
`permission`	No	Permission level for the token

TDQS

C2.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden but only states that a token is generated. It fails to disclose behavioral traits such as whether the token is immediately valid, if it overrides existing tokens, or if special permissions are required. The lack of side-effect information is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, making it concise, but it is too brief and lacks substantive content. While not verbose, it sacrifices clarity for brevity. A slightly longer description with key details would improve understandability without being wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no nested objects) and absence of annotations or output schema, the description is incomplete. It does not mention what the tool returns (e.g., the token string), any side effects, or potential errors. The description alone is insufficient for an agent to use the tool safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of parameters with descriptions, so the description adds minimal extra meaning. The baseline is 3. The description does not elaborate on the 'permission' enum values or the format of the 'database' name, but the schema is already clear.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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, prerequisites, or situations where it should not be used. The description lacks any context about the tool's intended use case or limitations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_databasesList all databases in your Turso organizationA

List all databases in your Turso organization

Name	Required	Description	Default
No parameters

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It implies a read-only, safe operation, but does not explicitly state that it does not modify state or require special permissions. Adequate for a simple list, but lacks explicit disclaimers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 9 words, perfectly concise with no wasted words. It delivers the essential information efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, no output schema, and a straightforward listing operation), the description provides complete context for an agent to understand its purpose and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters, so the description does not need to explain parameters. Baseline for 0 parameters is 4, and it meets that without adding unnecessary detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly indicates when to use the tool: when you need to see all databases. It does not explicitly state when not to use it or provide alternatives, but for a simple list operation, no further guidance is necessary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_tablesLists all tables in a databaseC

Lists all tables in a database

Name	Required	Description	Default
`database`	No	Database name (optional, uses context if not provided)

TDQS

C2.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It states the tool lists tables, implying a read-only operation, but does not disclose if it returns names only, includes system tables, or requires specific permissions. The behavior is minimally transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, clear sentence with no redundancy. Every word contributes to the purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with one optional parameter and no output schema, the description is adequate but lacks details on return format, ordering, or limitations (e.g., whether all tables include temporary tables). Some gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes the database parameter as optional and context-dependent. The description adds no further meaning beyond 'database', so baseline score of 3 applies (schema coverage is 100%).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 (e.g., describe_table for a single table, list_databases to enumerate databases). There is no mention of prerequisites or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

vector_searchPerforms vector similarity searchD

Performs vector similarity search

Name	Required	Description
`table`	Yes	Table name
`vector_column`	Yes	Column containing vectors
`query_vector`	Yes	Query vector for similarity search
`limit`	No	Maximum number of results (optional, default 10)
`database`	No	Database name (optional, uses context if not provided)

TDQS

D1.6/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description contains no behavioral traits such as read-only nature, authentication requirements, or side effects. It completely lacks transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one short sentence, but it is under-specified. It fails to convey essential information, making it too brief to be useful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters and no output schema, the description should explain the tool's behavior and return values. It provides none of these, making it severely incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides, so no improvement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tautological: description restates name/title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool versus its siblings (e.g., execute_query, list_tables). It fails to specify contexts or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

9 tool updatesv0.0.2May 6, 2026

Changedcreate_database5 fields changed

addedInput schema / $schema

Added value: +"http://json-schema.org/draft-07/schema#"

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / group / description

Previous value: -"Optional group name for the database"New value: +"Optional group name for the database (defaults to \"default\")"

changedInput schema / properties / name / description

Previous value: -"Name of the database to create"New value: +"Name of the database to create - Must be unique within organization"

changedInput schema / properties / regions / description

Previous value: -"Optional list of regions to deploy the database to"New value: +"Optional list of regions to deploy the database to (affects latency and compliance)"

Changeddelete_database3 fields changed

addedInput schema / $schema

Added value: +"http://json-schema.org/draft-07/schema#"

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / name / description

Previous value: -"Name of the database to delete"New value: +"Name of the database to permanently delete - WARNING: ALL DATA WILL BE LOST FOREVER"

Changeddescribe_table2 fields changed
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- addedInput schema / additionalProperties
```
Added value: +false
```
Changedexecute_query5 fields changed
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- addedInput schema / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / params / additionalProperties
```
Added value: +{}
```
- changedInput schema / properties / params / description
```
Previous value: -"Query parameters (optional)"New value: +"Query parameters (optional) - Use parameterized queries for security"
```
- addedInput schema / properties / params / propertyNames
```
Added value: +{
+  "type": "string"
+}
```
Addedexecute_read_only_query
Changedgenerate_database_token2 fields changed
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- addedInput schema / additionalProperties
```
Added value: +false
```
Changedlist_databases3 fields changed
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- addedInput schema / additionalProperties
```
Added value: +false
```
- removedInput schema / required
```
Removed value: -[]
```
Changedlist_tables3 fields changed
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- addedInput schema / additionalProperties
```
Added value: +false
```
- removedInput schema / required
```
Removed value: -[]
```
Changedvector_search2 fields changed
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- addedInput schema / additionalProperties
```
Added value: +false
```

8 tool updatesv1.0.0Mar 20, 2025
- First observedcreate_database
- First observeddelete_database
- First observeddescribe_table
- First observedexecute_query
- First observedgenerate_database_token
- First observedlist_databases
- First observedlist_tables
- First observedvector_search

Deploy Server

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

B3.1/5.0

Scored 2026-05-06 12:10 across 9 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: database CRUD, querying (read-only vs. destructive), schema inspection, token generation, listing resources, and vector search. No overlap or ambiguity.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (e.g., create_database, execute_query, list_tables), making the set predictable and easy to navigate.

Tool Count5/5

9 tools is well-scoped for a cloud database service covering management, querying, schema, tokens, and vector search. No unnecessary tools and no deficit.

Completeness4/5

Core operations are covered (CRUD for databases, query execution, schema inspection, token generation). Minor gaps like listing or revoking tokens exist, but the surface is mostly complete for typical workflows.

Maintenance

ActivityMaintained

ResponsivenessUnresponsive

Resources

Related MCP Connectors

hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
238
https://server.smithery.ai/@hithereiamaliff/mcp-nextcloud/mcp
AI2SQLOAuth
io.ai2sql
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Databases Developer Tools
1
https://builder.ai2sql.io/api/chatgpt-mcp
SupabaseOAuth
com.supabase
MCP server for interacting with the Supabase platform
Cloud Platforms Databases Developer Tools
32,988
https://mcp.supabase.com/mcp
mcp AOAuth
io.github.butterbase-ai
Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.
Databases RAG Systems Cloud Platforms
23,031
https://api.butterbase.ai/mcp

Related MCP Servers

MCP-Turso
Databases RAG Systems
nbbaier
A
license
A
quality
C
maintenance
A Model Context Protocol server that provides Claude access to Turso-hosted LibSQL databases, enabling database table listing, schema retrieval, and SELECT query execution.
Updated a year ago (2025-11-03 02:36 UTC)
4
19 npm
6
MIT
Supabase MCP Server
Databases Code Execution RAG Systems
Cappahccino
A
license
Not graded
quality
D
maintenance
A Model Context Protocol server that enables Claude and other LLMs to perform database operations and invoke Edge Functions within Supabase through natural language.
Updated 2 years ago (2025-03-21 20:13 UTC)
639 npm
4
MIT
@pilat/mcp-datalink
Databases Developer Tools
pilat
A
license
Not graded
quality
D
maintenance
MCP server for PostgreSQL, MySQL, and SQLite that gives AI assistants secure database access via the Model Context Protocol.
Updated 4 days ago (2026-10-27 21:39 UTC)
29 npm
5
MIT
mcp-turso-cloud
Databases Vector Databases
diegofornalha
A
license
Not graded
quality
D
maintenance
An MCP server that integrates Turso databases with LLMs, supporting organization and database-level operations with two-level authentication.
Updated a year ago (2025-08-02 10:27 UTC)
MIT

Appeared in Searches

Information about 'dex' or related topics