标签：#tools

The MCP (Model Context Protocol) ecosystem is growing fast. There are now hundreds of MCP servers available — but how do you know which ones are worth installing? After building and evaluating 60+ MCP servers ourselves, we developed a practical checklist that saved us from shipping broken tools. Here's the framework we use. The Problem Most MCP server listings tell you what the server does. Very few tell you how well it does it. You install something that sounds perfect, then discover: It activates on the wrong prompts (false positives) It pulls irrelevant context (retrieval drift) It sounds confident but gives wrong answers (ungrounded reasoning) It never improves from feedback Sound familiar? The 5-Dimension Evaluation Checklist Before installing any MCP server, ask these questions: 1. Trigger Precision Question: Does this server activate when (and only when) it should? Red flags: Overly broad trigger descriptions ("use for anything related to X") No documented activation conditions Activates on common words that appear in unrelated contexts Green flags: Specific, documented trigger scenarios Clear non-activation cases listed Tested against diverse prompts 2. Retrieval Quality Question: Does it pull the right context for the task? Red flags: Returns large chunks without filtering No citation or source tracking Retrieves plausible but outdated information Green flags: Targeted, minimal context retrieval Source attribution for every piece of context Version-aware (knows when data might be stale) 3. Reasoning Grounding Question: Are its conclusions tied to actual data? Red flags: Generates advice without referencing specific inputs Can't explain its reasoning chain Confident answers that contradict its own retrieved context Green flags: Every conclusion references specific evidence Explicitly flags uncertainty Gracefully handles missing information 4. Output Usefulness Question: Does the output actually solve your problem? Red flags: Generic responses that could appl

xAI has a bold pitch for Grok 4.5: it codes about as well as Claude Opus 4.8, but does it with roughly a quarter of the tokens. That's not a "we're smarter" claim. It's a "we're just as good for far less money" claim, which in 2026 might matter more. Someone actually put it to the test, so let me walk through what the numbers say and why you should care. The claim and the pricing Grok 4.5 landed on July 8, 2026. xAI says it matches Opus 4.8 on coding while using about 4.2 times fewer output tokens to get there. The sticker price already favors Grok. It runs $2 per million input tokens and $6 per million output. Opus sits at $5 and $25. That's less than half the price on both sides before you even factor in the token efficiency. Stack the two together and the cost gap gets dramatic. What the benchmarks say The benchmarks mostly support the marketing, with a catch. On Terminal-Bench 2.1, which measures real command-line work, Grok 4.5 scored 83.3 percent to Opus 4.8's 78.9. But on SWE-Bench Pro, the harder test of fixing real open-source bugs, Opus still comes out ahead. So the honest read is not "Grok is better." It's "Grok is about as good, for a lot less." Different claim, and a more interesting one. The hands-on test Benchmarks are one thing, real work is another. The New Stack ran a head-to-head, giving both models the same three jobs in one real Rust project (the fd file-finder) inside Cursor, and tracked every token. I'm summarizing their results here, credit to them for actually measuring it. The three tasks were a bug fix, a multi-file refactor, and a feature build. The code both models produced was nearly interchangeable, so the story came down to tokens, time, and cost. On the small bug fix, Opus actually won. Both wrote an identical fix with all tests passing, but Opus did it faster and on fewer tokens. Grok's efficiency edge showed up on the bigger jobs. On the refactor, Grok used about 197K tokens versus Opus's 954K for the same result, roughly a fifth.

Local-first desktop agent for everyday work Discussion | Link

Your people, your agents, your project — all in one place Discussion | Link

As developers, we end up needing to convert or resize a file constantly — a screenshot that needs to be a PNG for docs, an asset that needs to hit exact social-preview dimensions, a PDF that needs merging before a demo. Reaching for ffmpeg , imagemagick , or a paid SaaS every time is overkill for a one-off task. Here are two free, no-signup web tools that cover most of that day-to-day friction. 1. FreelyConvert — general-purpose file conversion freelyconvert.com A browser-based converter covering documents, images, video, and audio: 500+ formats — PDF, DOC/DOCX, images (JPG/PNG/GIF/BMP/SVG/WEBP), video (MP4/AVI/MOV/MKV), audio (MP3/WAV/FLAC/AAC), spreadsheets, presentations No account/signup — upload, convert, download Batch conversion for multiple files in one pass Auto-delete after 24 hours and SSL encryption in transit Useful specifically for: PDF ↔ image conversions ( pdf-to-jpg , images-to-pdf ) Merging PDFs without touching a CLI tool Compressing video/audio for quick sharing Quick image compression when you don't want to script it 2. ImageResizer.dev — client-side image resizing/conversion imageresizer.dev This one's worth calling out for devs specifically: it runs entirely client-side via the Canvas API — nothing is uploaded to a server. That's a real difference if you're resizing anything you'd rather not send off-device, and it also means it's fast (no upload/download round trip). Features: Exact dimension presets for social platforms (Instagram, LinkedIn, X/Twitter, YouTube, TikTok, Pinterest, WhatsApp) — handy for generating OG images or social preview assets without hardcoding dimensions yourself Format conversion across JPG, PNG, WebP, AVIF, BMP, GIF, SVG Crop, flip, upscale , plus bulk resize/compress for batches Aspect-ratio locking to avoid distortion No account, no watermark Good fit for generating og:image assets, favicon prep, or resizing screenshots for a README without spinning up a script. Why bother mentioning these Neither requires an accoun

An MCP server for GPs Discussion | Link

Universal XY Converter est un plugin QGIS pratique qui simplifie la conversion, la manipulation et le traitement rapide de coordonnées géographiques et projetées directement au sein de votre environnement de travail. 🎥 Tutoriel vidéo Découvrez la prise en main pas à pas en vidéo : 📖 Documentation complète Consultez le manuel d'utilisation officiel sur GitHub : 👉 User Manual - QGIS Plugin Universal XY Converter 🌟 Fonctionnalités clés Conversion rapide de coordonnées : Transformez facilement des paires de coordonnées (X, Y) entre différents systèmes de référence spatiales (CRS). Import & Traitement par lot : Prise en charge fluide de listes de points pour accélérer le traitement de vos relevés de terrain. Gain de temps au quotidien : Évite les manipulations manuelles complexes ou l'utilisation d'outils externes pour vérifier et convertir vos données de géolocalisation. 🚀 Comment les installer et démarrer ? Ouvrez QGIS . Allez dans le menu Extensions > Installer/Gérer les extensions . Dans la barre de recherche, tapez XY Converter (ou Universal Map2web ). Sélectionnez l'extension puis cliquez sur Installer l'extension . 💬 Vos retours m'intéressent ! Avez-vous testé ces outils ? N'hésitez pas à laisser un commentaire ci-dessous avec vos retours, vos questions ou vos idées d'amélioration !

Executive Leadership Focused on Growth and Innovation Discussion | Link

Turn messy bank exports into clear financial decisions Discussion | Link

This week's releases cluster around a theme: reducing the overhead that compounds in production agentic systems. Gemini 3.6 Flash ships with measurable token reduction and a price cut, Vercel's AI Gateway gets service tier routing for latency-cost tradeoffs, and Python cold starts quietly drop by half with zero code changes required. Nothing experimental here—most of this is worth touching immediately if you're already in these ecosystems. Gemini 3.6 Flash cuts output tokens by 17% Google's 3.6 Flash reduces output token usage by 17% versus 3.5 Flash while lowering cost to $1.50/1M input and $7.50/1M output. The improvement is most pronounced on coding and web tasks, which happen to be the workload profile of most production agents. The companion model, 3.5 Flash-Lite, trades some quality for throughput—350 output tokens/sec—at $0.30/$2.50 per million tokens. Token efficiency isn't a vanity metric in agentic systems. Multi-step workflows compound output costs: every intermediate reasoning step, tool call response, and context accumulation multiplies what you pay. A 17% reduction per model call can translate to significantly more than 17% savings across a full agent loop, depending on how many hops your workflow runs. The throughput number on Flash-Lite matters too—if you're running high-volume document classification or search reranking, 350 tokens/sec opens architectures that weren't cost-viable before. The API swap is a single parameter change. No migration friction, no new authentication surface. Ship it now if Gemini is already in your stack and you're paying attention to inference costs. Replace 3.5 Flash with 3.6 Flash for general agentic tasks; move high-throughput, lower-stakes subtasks to Flash-Lite. Gemini 3.6 Flash and 3.5 Flash-Lite on AI Gateway Both new Gemini models are immediately available through Vercel's AI Gateway, callable via the unified AI SDK with the same cost tracking, failover, and routing you'd use for any other provider. Model selection

Increase your brand's AI visibility on autopilot Discussion | Link

Permission-first real-time senses for AI companions Discussion | Link

A human-in-loop support agent that tracks customer signals Discussion | Link

A private data-usage meter for your Mac menu bar Discussion | Link

Track Codex and Claude Code and respond from your Notch Discussion | Link

Made for introverts to remember people & reconnect naturally Discussion | Link

The power of Codex with local, self-hosted models and voice Discussion | Link

Dead-Simple IoT Push Notifications for Makers & Hobbyists Discussion | Link

Highlight text on any page and turn it into audio. Discussion | Link

Back on 2026-07-14 I found and fixed a real landmine in this repo: requirements.txt had mcp[cli] with no version constraint at all. Any fresh install could pull in a breaking major version with zero warning. I pinned it to mcp[cli]>=1.28.0,<2.0.0 and moved on, feeling like I'd closed the gap. I hadn't. I'd only pinned the library . The actual contract my MCP server exposes to any agent that connects to it — the tool names, parameter shapes, and descriptions an LLM reads to decide how to call my code — isn't a version string anywhere. It's generated fresh, every time the server boots, from whatever my function signatures and docstrings happen to say at that moment. Nothing pins that. Nothing diffs it. Nothing tests it. What actually generates the contract My server ( server.py ) is a FastMCP app with plain @mcp.tool() -decorated functions: @mcp.tool () def create_article ( title : str , body_markdown : str , tags : list [ str ] = None , published : bool = False ) -> dict : """ Create a new DEV.to article. Returns id and url. """ payload = { " article " : { " title " : title , " body_markdown " : body_markdown , " published " : published }} if tags : payload [ " article " ][ " tags " ] = tags result = _dev ( " /articles " , method = " POST " , data = payload ) return { " id " : result [ " id " ], " url " : result . get ( " url " ), " published " : result . get ( " published " )} FastMCP inspects that signature at import time and builds the JSON Schema an agent actually sees — parameter names, types, which ones are required, and the docstring as the tool's description. I never write that schema by hand and I never check it in anywhere. It's derived, every run, from source that I edit for completely unrelated reasons. That's the gap. requirements.txt pinning stops FastMCP's own behavior from shifting under me between installs. It does nothing about my behavior shifting the schema FastMCP generates from my code, on every single commit, with no separate review step. Where