Connector Lets AI Agents Query Basque Government Open Data via Filters and SPARQL

·1 views

A developer describes an MCP connector that gives AI agents access to Open Data Euskadi, the Basque Government's public data portal. It offers two tools: search_euskadi_content, which supports strict metadata filters such as language and date ranges for targeted catalog lookups, and execute_sparql_query, which enables graph traversal over linked open data. The article argues that semantic, relationship-aware querying lets researchers uncover connections between grants, contracts, and environmental data without manual CSV exports. The connector is built on the author's MCPFusion framework, which is designed for consistent error handling and reliability under load. The piece also raises questions about how much trust to place in agents with read or write access to public registries.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Does a Cloned Voice Stay the Same? Scoring Qwen3-TTS With ECAPA

Written with AI assistance. Every number comes from my own runs; if you spot an error, tell me and I'll fix it. I had Qwen3-TTS 1.7B read two long narrations, one in Korean and one in English, and scored every sentence chunk against the voice sample using ECAPA speaker embeddings. In these two runs, English held steady and Korean wandered more: the English narration had a median similarity of 0.861 and no chunk below 0.75, while the Korean one had a median of 0.806, with 10 of its 51 chunks under 0.75. The practical lesson is short.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Detecting Website Technologies: Why Reliable Domain Analysis Is Hard

A developer building SalesData.in, a domain-intelligence platform, explains the difficulties of identifying the technologies behind a website. Detection is complicated because sites may conceal fingerprints, serve assets through CDNs, customize installations, or run several technologies at once. Relying on one signal risks false positives and false negatives, so the approach combines evidence such as HTML patterns, asset paths, HTTP headers, DNS records, and SSL data. Engineering challenges include handling incomplete responses, keeping records consistent across rescans, validating detection rules against real sites, and distinguishing missing signals from failed scans. The author notes that technology detection is only one part of broader domain analysis.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

UE5 Devlog Details Blueprint Sprint and Stamina System Linked to Hydration and Health

A developer's devlog describes a Blueprint-based sprint and stamina system built in Unreal Engine 5 and tied to the player's health and thirst. Hydration drains at a steady rate while walking, and sprinting uses stamina while speeding up that loss. When stamina runs out, the added sprint drain stops, but the normal drain continues. Reaching zero hydration causes the player to start losing health, so resource management becomes part of movement. Drinks restore hydration, medkits recover health, and the UI highlights critical levels as resources drop.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Student Builds Offline App That Turns Lectures and PDFs into Summaries and Flashcards

A developer has released Lazy Student AI, a free desktop application that runs entirely offline to help students study. Users drop in a lecture video, audio file, or PDF, and the app extracts the text, then generates bullet-point summaries and interactive flashcards. The tool uses Google's open-weight Gemma 2B model via Ollama for summarization, with OpenAI's Whisper and FFmpeg handling speech transcription, all orchestrated by a Spring Boot backend. The developer emphasized zero running costs and privacy, since lecture content never leaves the user's machine. The project was submitted to a Hacktoberfest open-source AI challenge.

0 comments Read more at DEV Community