"How to interact with SQL databases" matching MCP connectors:

Search scientific papers with structured experimental data from full-text studies

DC Hub is the neutral, real-time data layer for data-center infrastructure, exposed as a Model Context Protocol server so any AI agent can both query it and cite it. Coverage: 21,000+ facilities (search, profile, score, alternatives); 232 markets scored by the DCPI Data Center Power Index; the DCGI Data Center Gas Index (per-state natural-gas suitability for siting); live grid telemetry across 7 US ISOs (fuel mix, carbon intensity, demand, prices) plus a one-call all-ISO scoreboard; interconnection-queue depth; 2,000+ tracked M&A deals and a hyperscaler-capex tracker; and site factors. — fiber routes, water-stress, tax incentives, nearby substations & transmission. Why agents choose it: it's the only data-center-intelligence source an LLM can query live and cite — every full-data response includes a Source: DC Hub, CC-BY-4.0 attribution line. It's the MCP-native alternative to quarterly PDF research: live JSON, no contracts, no NDAs. Access: Streamable HTTP at https://dchub.cloud/mcp. Free tier with no signup; free email-verified dev key for higher limits; paid tiers for full data volume.

A Model Context Protocol server that provides Philippine License to Sell (LTS) verification data to LLMs. Built on Cloudflare Workers with Supabase. Public, read-only, no authentication required. Data sourced from the Department of Human Settlements and Urban Development (DHSUD) License to Sell registry and cross-referenced with published real estate projects on REN.PH.

MCP server for the Philippine Standard Geographic Code (PSGC) API. Gives AI agents structured access to the full PH geographic hierarchy - regions, provinces, cities, municipalities, and barangays.

Reverse geocode latitude/longitude to loc_id; resolve loc_ids to boundaries, centroids, hierarchy.

Read-only access to the Islam West Africa Collection via Hugging Face datasets.

Reviewed public-data search and execution with provenance and verifiable integrity receipts.

Software entry prices for 16 categories, with ratings and true 3-year cost. CC BY 4.0

Origin-signed US political data: 25,546 officials, bills, votes, positions with sources.

Search structured COMPAMIR news in Japanese and English, with links to source reports.

Public fellowship and grant search with sourced details and live filter vocabularies.

Business-published entity records with confirmation dates: look up, page feeds, check claims.

Agent integration with the Northwestern University Libraries Digital Collections API

One MCP endpoint over 75 public PPN APIs: search_apis to discover, execute_api to call. Free tier.

Query normalized U.S. Congress STOCK Act trades with member, ticker, and performance data.

Free access to 3.3M French & EU court decisions + 1.5M law articles w/ history. 31 read-only tools

Funding stress early warning for US money markets from free public data, with an honest backtest.

Verified Japanese company press releases with provenance (corporate number, source URL) and jobs.

Public, read-only access to ~3.9M Romanian companies (data from ONRC, ANAF, and the Ministry of Finance). Five tools: search & filter companies by name, CAEN activity, county, revenue/profit/employee ranges, and VAT status; fetch a company profile by CUI; yearly financial history; public status flags (VAT, insolvency, dissolution, e-Factura); and CAEN activity-code lookup. No authentication required.

MCP server for Project Gutenberg — 75,000+ public-domain ebooks with full plain-text retrieval.