目录 / baselight-mcp
baselight-mcp
Baselight is the antidote to AI hallucinations: a unified data layer that serves as the structured backbone for intelligent systems, connecting both humans and LLMs to verifiable, auditable facts. It provides a suite of tools—including an AI for explainable intelligence, an extensive catalogue of dependable structured data, and a studio for transparent analysis—to ensure that every query is answered with truth, not guesswork, powering smarter, more reliable insights for everyone. Baselight’s MCP server lets you seamlessly integrate your favourite applications with the Baselight platform. By connecting to the MCP server, you can browse, discover, and query 70,000+ datasets and 450+ billion rows directly from your preferred environment—whether you’re building, analysing, or exploring.
接入信息
- 传输形态
- http
- 鉴权方式
- 需 API Key（需要配置：BASELIGHT_API_KEY）
- 端点
https://baselight-mcp.run.tools
{
"mcpServers": {
"baselight-mcp": {
"headers": {
"Authorization": "Bearer \u003cYOUR_KEY\u003e"
},
"url": "https://baselight-mcp.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| baselight_ping | Simple ping test to verify MCP server is responding |
| baselight_search_catalog | Search the catalog for datasets using a text query and filters. Datasets in Baselight have the following format: @username.dataset. Datasets can be public or private — you can search and use all public datasets as well as the user's private datasets. This is typically the first step in the discovery workflow. |
| baselight_search_tables | Search for tables using a text query and filters. Tables in Baselight have the following format: @username.dataset.table. Tables are grouped into datasets which can be public or private — you can search and use all public datasets as well as the user's private datasets. Search for tables directly when you are unable to find relevant datasets. |
| baselight_get_dataset_metadata | Retrieve detailed schema and metadata for a specific dataset using Baselight format @username.dataset. Use this after discovering datasets to understand their structure before querying. Tables within datasets follow the format @username.dataset.table (always double-quoted identifiers in SQL). |
| baselight_get_dataset_tables | Retrieve a paginated list of tables from a specific dataset using Baselight format @username.dataset. Use this tool to browse datasets with many tables or to search for specific tables within a dataset. Each page returns up to 100 tables with metadata. |
| baselight_get_table_metadata | Retrieve detailed schema and metadata for a specific table using Baselight format @username.dataset.table. Use this to understand table structure, column types, and constraints before writing SQL queries. Tables must be referenced in SQL with double quotes. |
| baselight_get_user | Retrieve detailed information about a Baselight user including their profile bio, website, and public datasets. Use this to understand who owns datasets you're interested in. |
| baselight_sdk_query_execute | Execute a SQL query on Baselight and wait for results (up to 1 minute). The query executes and returns the first 100 rows upon completion, or info about a pending query that needs more time. Use DuckDB syntax only, table format "@username.dataset.table" (double-quoted), SELECT queries only (no DDL/DML), no semicolon terminators, use LIMIT not TOP. If query is still PENDING, use `sdk-get-results` to continue polling. If totalResults > returned rows, use `sdk-get-results` with offset to paginate. |
| baselight_sdk_get_results | Retrieve results from a previously executed SDK job using the resultId from `sdk-query-execute`. If the query is complete, returns results immediately. If still pending, polls for up to 1 more minute. Use this after `sdk-query-execute` returns PENDING status. |
提交举报 / 纠错
侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。