技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 701 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：baselight-mcp
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill is an instruction-only connector for querying the Baselight MCP dataset service; its requirements and instructions are generally coherent with its stated purpose, with only a minor omission (it mentions needing an API key/OAuth but does not declare required credentials in metadata).
目的
Name, description, and runtime instructions consistently describe a data-query connector for the Baselight MCP server and the listed dataset sources. Nothing in the SKILL.md asks for unrelated services or capabilities.
说明范围
SKILL.md provides discovery/query workflow, the MCP server URL, SQL syntax examples, and troubleshooting; it does not instruct the agent to read unrelated files, system paths, or to exfiltrate data. All steps stay within the connector/querying scope.
安装机制
Instruction-only skill with no install spec and no code files — lowest-risk install posture. Nothing will be written to disk by the skill itself.
证书
SKILL.md states a Baselight account or API key (or OAuth) is required, but the registry metadata lists no required environment variables or primary credential. This is a minor inconsistency: the skill itself does not demand unrelated secrets, but the metadata should declare how credentials are provided.
持久
always is false and the skill is user-invocable; it does not request elevated or persistent platform privileges and does not instruct modifying other skills or global settings.
综合结论
This skill is an instruction-only connector for Baselight's MCP and appears coherent. Before installing: (1) Confirm you trust the Baselight service URL (https://api.baselight.app/mcp) and the public docs; (2) Prefer authorizing via OAuth where supported instead of pasting API keys into chat; (3) If you must supply an API key, use the platform's secure credential storage and limit the key's scope and lifetime; (4) Check rate limits, billing, a…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Baselight data via MCP」。简介：Connects to the Baselight MCP (Model Context Protocol) server to discover and q…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/pjsousa79/baselight-mcp/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
description: Connects to the Baselight MCP (Model Context Protocol)
server to discover and query 50+ premium dataset sources including Kaggle,
OWID, World Bank, Data Commons, Eurostat, FiveThirtyEight, DefiLlama,
EVM blockchains, Polymarket, NFLverse, Yahoo Finance, FRED, IMF, SEC
filings, OECD, US Census, CDC, FBI Crime, CIA World Factbook, sports
(soccer, basketball, fantasy football), weather (Open-Meteo), crypto
(XrpScan, XRPL, CoinDesk), and education/health statistics. Run live
SQL queries against structured data from AI tools.
homepage: "https://baselight.ai/docs/connecting-to-the-baselight-mcp-server/"
metadata:
openclaw:
emoji: 🔌
requires:
name: baselight-mcp
---
# Baselight MCP
Use Baselight via MCP to browse, discover, and query Baselight datasets
directly from your AI tool or IDE.
MCP Server URL: https://api.baselight.app/mcp
## When to Use This Skill
- User wants datasets for a topic
- User wants structured tables
- User wants SQL analysis
- User wants verifiable results
## Quick Start
Connect using OAuth or API key depending on client.
### OAuth Clients
- ChatGPT connectors
- Claude Web/Desktop
### API Key Clients
- VS Code
- Gemini CLI
- LibreChat
------------------------------------------------------------------------
## Workflow
1. Understand question
2. Discover datasets
3. Inspect schema
4. Query data
5. Return results + SQL
------------------------------------------------------------------------
## Query Format
Tables use:
@username.dataset.table
Example:
SELECT * FROM @user.soccer.matches LIMIT 10;
------------------------------------------------------------------------
## Best Practices
- Discover first
- Inspect schema
- Query iteratively
- Include SQL
- Explain assumptions
------------------------------------------------------------------------
## Limitations
- Requires Baselight account or API key
- Query limits may apply
- Dataset freshness varies
------------------------------------------------------------------------
## Troubleshooting
Connection fails: - Verify MCP URL - Reauthenticate or regenerate key
Unauthorized: - Invalid key or expired OAuth
Slow query: - Reduce scope - Add LIMIT
------------------------------------------------------------------------
## Support
Docs: https://baselight.ai/docs/connecting-to-the-baselight-mcp-server/
App: https://baselight.app