mcp-steampipe
蒸汽管道 MCP
这是一个简单的 Steampipe MCP 服务器。它充当 AI 模型和 Steampipe 工具之间的桥梁。
先决条件
已安装 Python 3.10+。
安装了 uv(我的最爱)和 mcp[cli]
蒸汽管道已安装并运行。
Steampipe 插件已配置(例如,github)并带有必要的凭证(例如,~/.steampipe/config/github.spc 中的令牌)。
任何支持 MCP 的 LLM 都可以。我这里用的是 Claude。
安装了 Node.js 和 npx(MCP Inspector 需要并且可能运行某些 MCP 服务器)。
Related MCP server: mcp-mssql-server
运行 MCP 拦截器
这是一个非常棒的工具,可以测试您的 MCP 服务器是否按预期运行
运行拦截器
npx -y @modelcontextprotocol/inspector uv --directory . run steampipe_mcp_server.py应打开一个带有 MCP Inspector UI 的浏览器窗口(通常位于http://localhost:XXXX )。
等待左侧面板上的“已连接”状态。
转到“工具”选项卡。
您应该会看到 run_steampipe_query 工具及其描述。
单击工具名称。
在“参数”JSON 输入字段中,输入有效的 Steampipe 查询:
{
"query": "select name, fork_count from github_my_repository "
}执行并查看json结果
运行工具
非常简单。只需运行拦截器并确保该工具在目录中正常运行。然后将服务器配置添加到相应的 LLM,并从 LLM 中选择该工具。
故障排除
如果在拦截器中找不到该工具,则意味着@mcp.tool() 装饰器存在一些问题。
执行错误 - 查看检查器中的“结果”以及终端中的服务器日志(stderr)。Steampipe 是否运行?是否存在 SQL 错误?超时?JSON 解析错误?请相应地调整 Python 脚本。
tail -f ~/Library/Logs/Claude/mcp.log
tail -f ~/Library/Logs/Claude/mcp-server-steampipe.log安全风险Claude 在此 POC 中盲目执行您的 SQL 查询,因此有可能使用您配置的凭据通过 Steampipe 生成和执行任意 SQL 查询。
Available Tools
1 toolrun_steampipe_queryB
Executes a SQL query using the Steampipe CLI and returns the results as a JSON string.
Args: query: The SQL query to execute via Steampipe (e.g., "select login from github_user limit 1"). Ensure the query is valid Steampipe SQL.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The naming follows a clear verb_noun pattern (run_steampipe_query).
A single tool is too few for most practical purposes, as it severely limits the server's functionality and flexibility. While it might cover the basic query execution, it lacks any supporting operations like listing available tables, checking query status, or managing connections.
The server is severely incomplete for interacting with Steampipe. It only provides query execution, missing essential operations such as listing available plugins/tables, describing table schemas, managing connections, or handling query errors and metadata. This will cause significant agent failures in complex workflows.
Maintenance
Related MCP Connectors
Query your warehouse or a CSV with Claude/ChatGPT over MCP, governed by table-level ACL + audit.
Read and write NetSuite and run SuiteQL from Claude or ChatGPT. Write tools flagged for approval.
Hosted PostgreSQL MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables interaction with SQLite databases, filesystem, AWS IAM, and Gmail through a master MCP server with a Streamlit UI optimized for Claude.1-
- AlicenseNot gradedqualityDmaintenanceEnables Claude Code and other MCP clients to interact with Microsoft SQL Server databases through standardized tools for query execution, schema exploration, table management, and stored procedure execution.95 npm1MIT
- AlicenseAqualityCmaintenanceExposes PostgreSQL query execution, EXPLAIN, and schema inspection tools to MCP-compatible clients like Claude Desktop.31MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude to query a Postgres analytics schema via a read-only MCP server, with tools auto-generated from live database introspection and configurable SQL queries defined in YAML.MIT