Explore

🚀 Improve patent analysis with a high-performance MCP server for USPTO Final Petition Decisions, featuring context reduction and customizable fields.

in the readmeuspto_fpd_mcp - Fast API Access for Patent Research ## 📥 Download ![Download uspto_fpd_mcp ]( ## 📖 Description The **uspto_fpd_mcp** is a high-performance server designed

Python·MIT·★ 4·Few stars·No key

A multi-server Discord control plane that exposes Discord operations as MCP tools, resources, and prompts for AI clients, with a built-in conversational AI agent.

Skill·Apache-2.0·★ 9·No key

Scrape job listings from companies using Greenhouse ATS via a fast API.

Hosted by author·No license·Few stars·No key

MCP server to drive Firefox-based browsers (Floorp, LibreWolf, Waterfox, Zen, Mullvad, Firefox) from Claude Code, Cursor & any MCP client - read pages, screenshot, automate tabs & forms in your real s

in the readmeAPI. Set `floorp.mcp.enabled = true` in `about:config` and gecko-mcp uses the fast ` API — no extension, richest feature set. - **Any other Gecko browser** — launch it with

Node.js·MIT·★ 2·Few stars·No key

Pro+ subscription required. Tenant-wide Power Automate monitoring using the FlowStudio MCP cached store: failure rates, run-health trends, maker/app inventory, inactive owners, and compliance/health r

in the skill textand inventory tenant assets through the FlowStudio MCP **cached store** — fast reads, no PA API rate limits, and enriched with governance metadata and remediation hints. > **⚠️ Pro

Official·Skill·MIT·★ 40k in collection·No key

Generate images using AI. Use when asked to generate, create, or make images, textures, icons, sprites, artwork, visual assets, or mockups. Supports OpenAI (gpt-image-2) and Google Gemini (Nano Banana

in the skill textper image - **Google Gemini (Nano Banana)** — Fast, free tier available, great for iteration 2. Direct them to get an API key: - OpenAI → - Gemini → 3. Once they

Official·Skill·MIT·★ 40k in collection·No key

Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'BM25 or sparse vectors?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from

in the skill textenough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', 'ColBERT reranking', or 'missing keyword matches' # How to Improve Search Results with Advanced

Official·Skill·MIT·★ 40k in collection·No key

Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded

in the skill textbatching and parallelism: - Use batch upserts (64-256 points per request) Points API - Use 2-4 parallel upload streams For server-side, optimize Qdrant configuration and

Official·Skill·MIT·★ 40k in collection·No key

Configures best-practice, high-signal alerting policies for Cloud Run resources on Google Cloud (services, jobs, and worker pools) based on seasoned SRE practices. Use when analyzing, recommending, wr

in the skill textstrictly on actionable user impact and scaling bounds. -------------------------------------------------------------------------------- ## CRITICAL RULES * **Prompt-First Fast Path (Skip Discovery When Named)**: * **If the user prompt explicitly specifies the target

Official·Skill·Apache-2.0·★ 21k in collection·No key

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results

in the skill textbill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests

Official·Skill·MIT·★ 32k in collection·No key

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

Skill·MIT·★ 31k·No key

Generate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. Use for homolog search, UniRef30/ColabFold env searches, A3M or FASTA alignments, paired MSA sear

in the skill textAPI calls, or local Docker deployment. For local deployment, download the databases in parallel with aria2c and launch via NIM_MODEL_NAME (the recommended default fast

Official·Skill·Apache-2.0 AND CC-BY-4.0·★ 3.6k in collection·No key

Use this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host ↔ DPU PCIe control-plane messaging, picking server (DPU) vs client (host) roles, choosing s

in the skill textfast-path producer / consumer, querying max-msg-size or max-clients capabilities, registering connection callbacks, or debugging DOCA_ERROR_* returns from the Comch API. Trigger even

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Build, migrate, and deploy Next.js apps on Cloudflare Workers with vinext. Use when starting a Next.js project on Cloudflare, moving an existing app to Workers, choosing between vinext and OpenNext, o

in the skill textthe Next.js API surface on Vite: - Familiar Next.js development: App Router, Pages Router, React Server Components, and supported `next/*` imports. - Vite tooling: fast HMR, native ESM

Official·Skill·Apache-2.0·★ 3.1k in collection·No key

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

in the readmetrajectories as readable Markdown, then syncs local SQLite and LanceDB indexes for fast retrieval and self-evolving reuse. Title EverOS Other Agent Memory Libraries Markdown source

Python·Apache-2.0·★ 13k·No key

📻Free and open-sourced terminal/ssh/sftp/ftp/telnet/serialport/RDP/VNC/Spice client(Linux, Mac, Windows, Android, HarmonyOS, iOS)

in the readmeleading AI models through PackyCode with one API endpoint and one API key. Enjoy fast, reliable access with automatic failover and dedicated high-speed routes for

Skill·MIT·★ 15k·No key

Google Flights MCP, CLI and Python Library

in the readmedirectly interacts with Google Flights' API > through reverse engineering. > This means: > > * **Fast**: Direct API access means faster, more reliable results > * **Zero Scraping**: No HTML parsing

Python·MIT·★ 3.2k·No key

Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.

in the readmeleading AI models through PackyCode with one API endpoint and one API key. Enjoy fast, reliable access with automatic failover and dedicated high-speed routes for

Skill·GPL-3.0·★ 13k·No key

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

in the readmeFast and Accurate Code Search for Agents Uses ~99% fewer tokens than grep+read Quickstart • CLI • MCP Server • Installation • Benchmarks Semble is a code search library

Python·MIT·★ 6.2k·No key

🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.

in the readmeWorkflow Status ]( ![AI Policy: Human Voice ]( ![Discord ]( ![Sponsors ]( Cloud | Installation | Website | Discord Fast, simple, open-source project management. ## Built for your team's work - **See work

Skill·MIT·★ 9.5k·No key

Your memories are in ChatGPT... But nowhere else. Universal Memory MCP makes your memories available to every single LLM. No logins or paywall. One command to set it up.

in the readmeinstructions on the page. ## Features - 🚀 Built on top of the Supermemory API , extremely fast and scalable. - ✅ No login required - 😱 Completely free to use - Extremely simple setup

Skill·MIT·★ 1.7k·No key

Allows you to emulate an Android native library, and an experimental iOS emulation

in the readmedebugging with Cursor and other AI tools. - Emulation of the JNI Invocation API so JNI_OnLoad can be called. - Support JavaVM, JNIEnv. - Emulation of syscalls instruction

Skill·Apache-2.0·★ 5.3k·No key