MCP.so
ログイン

SQLite MCP Server

@prayanks

SQLite MCP Server について

These are MCP server implementations for accessing a SQLite database in your MCP client. There is both a SDIO and a SSE implementation.

基本情報

カテゴリ

データベース

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

prayanks

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-sqlite-server": {
      "command": "python",
      "args": [
        "create_db.py"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is SQLite MCP Server?

SQLite MCP Server is a Python-based MCP server that connects to a SQLite database (e.g., containing startup funding data). It exposes table schemas as resources, provides a read-only SQL query tool, and offers prompt templates for data analysis tasks. Designed for MCP clients and language models, it communicates via the STDIO protocol.

How to use SQLite MCP Server?

Create a virtual environment, install mcp[cli] with pip, and run python sqlite_mcp_server.py. For use with Claude Desktop, add a JSON configuration block specifying the python -u command with the absolute path to the script. Access resources like schema://sqlite/all, invoke the sql_query tool with SELECT statements, and use prompts such as analyze_table_prompt.

Key features of SQLite MCP Server

  • Exposes table schemas as MCP resources (schema://sqlite/{table}).
  • Provides a sql_query tool for read-only SELECT queries only.
  • Offers prompt templates: analyze_table_prompt and describe_query_prompt.
  • Communicates via STDIO (reads from stdin, writes to stdout).
  • Logging via Python’s logging module (configurable to file or stderr).

Use cases of SQLite MCP Server

  • Let an LLM explore and summarize startup funding data.
  • Generate natural‑language insights from a SQLite database.
  • Debug or test SQL queries through an MCP‑compatible client.

FAQ from SQLite MCP Server

What dependencies are required?

Python and the mcp[cli] package (installed via pip). The SQLite database must be created beforehand (e.g., using the provided create_db.py script).

How does the server handle SQL queries?

Only SELECT statements are allowed; the server enforces read‑only access.

How is the server deployed or integrated?

It runs as a local process communicating via STDIO. It can be added to Claude Desktop by updating the MCP servers configuration with the correct command and arguments.

Where can I see logging output?

By default logs are written to stderr. You can configure logging to a file (e.g., mcp_server.log) and set the level (e.g., DEBUG).

What transport does the server use?

It uses the STDIO protocol – it reads JSON‑RPC messages from standard input and writes responses to standard output.

コメント

「データベース」の他のコンテンツ