広告掲載
MCP.so
ログイン

Tailpipe MCP Server

@turbot

リポジトリ

基本情報

カテゴリ

その他

ライセンス

Apache-2.0

トランスポート

stdio

作者

turbot

Tailpipe MCP Server について

Enable AI assistants to explore and query your Tailpipe data!

#ai#mcp#turbot-pipes#tailpipe#mcp-server

Tailpipe MCP Server の設定

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": {
    "tailpipe": {
      "command": "npx",
      "args": [
        "-y",
        "@turbot/tailpipe-mcp"
      ]
    }
  }
}

Tailpipe MCP Server のツール

10

Run a read-only Tailpipe SQL query using DuckDB syntax

Initialize or refresh the DuckDB session from a Tailpipe init SQL script

List all available Tailpipe partitions with simple statistics

Show details of a specific Tailpipe partition

List all available Tailpipe tables

Show details of a specific Tailpipe table and its columns

List all Tailpipe plugins installed on the system

Get details for a specific Tailpipe plugin installation

List all Tailpipe sources available on the system

Get details for a specific Tailpipe source

概要

What is Tailpipe Model Context Protocol (MCP) Server?

The Tailpipe MCP Server connects AI assistants like Claude to cloud and SaaS logs via Tailpipe, enabling natural language exploration and analysis of log data. It provides safe, read-only SQL access to data from CloudTrail, Kubernetes, and other cloud services.

How to use Tailpipe Model Context Protocol (MCP) Server?

Install Node.js v16+ and Tailpipe, then add the MCP server configuration to your AI assistant's config file using npx -y @turbot/tailpipe-mcp. Ask natural language questions about your logs—the LLM handles SQL translation automatically.

Key features of Tailpipe Model Context Protocol (MCP) Server

  • Read-only SQL queries against Tailpipe log data
  • Natural language log exploration and analysis
  • Works with CloudTrail, Kubernetes, and cloud logs
  • Tools for listing tables, partitions, plugins, and sources
  • Status resource for connection verification
  • Configurable via environment variables

Use cases of Tailpipe Model Context Protocol (MCP) Server

  • Security incident investigation using natural language queries
  • AWS cost and performance analysis across services
  • Timeline reconstruction of user activity sessions
  • Risk analysis from CloudTrail error patterns
  • Query development assistance for Tailpipe SQL

よくある質問

1

What are the prerequisites to use this server?

Node.js v16 or higher and a local Tailpipe installation that is configured with your cloud and SaaS log data.

2

Can this server modify my log data?

No, it provides read-only access to log data through DuckDB SQL queries.

3

How do I connect to a specific init SQL script?

Pass the script path as a command line argument in the MCP config, or set the `TAILPIPE_MCP_INIT_SCRIPT_PATH` environment variable.

4

What AI assistants are supported?

The README documents setup for Claude Desktop and Cursor, with MCP configuration files specific to each.

5

Is this open source?

Yes, published under the Apache 2.0 license by Turbot HQ, Inc. Commercial use of the Tailpipe product falls under separate terms.

コメント

「その他」の他のコンテンツ

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K
広告掲載