Keenable SELECT: an agent that searches the web in SQL
Keenable SELECT is a new MCP server that allows AI agents to perform web searches using SQL queries. By integrating semantic operators directly into SQL, it enables efficient data extraction and filtering across thousands of pages without the high cost of traditional LLM token processing.
Why it matters
This tool represents a significant shift in AI agent architecture, moving from expensive, inefficient LLM-based web parsing to structured, query-based data retrieval.
Research reports built by Keenable SELECT , an agent that searches the web in SQL. Every card links the finished report and the full trajectory behind it: each query, tool result, and result set.
“Which AI researchers moved between frontier labs since 2025 ? For each move list the researcher , the lab they left , where they went and the month .”
SELECT SEM_EXTRACT(content, 'researcher' ), SEM_EXTRACT(content, 'left lab' ), SEM_EXTRACT(content, 'joined lab' ), SEM_EXTRACT(content, 'move month' ) FROM WEB_SEARCH(8 diverse queries) WHERE SEM_MATCH(content, 'named researcher moving between frontier labs , 2025+ ') You get a report
Keenable SELECT is an MCP server with one main tool: select . The tool runs one read-only DuckDB SELECT statement on live web data. The server runs the web and semantic operators outside DuckDB, puts their output back into the row set, and then runs the final SQL in DuckDB.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in