26,389 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
NotebookLM-quality document Q&A with per-passage citations via official Gemini File Search API. Upload docs, ask questions, get zero-hallucination answers with structured citations. Runs locally from the @mcpware/notebooklm-api npm package. Needs 1 environment variable to run.
★not rated 2 yesterdayA
tokens not measured
originalMIT
Use when a user asks for a literature review, survey, "related work", or "what's the state of the art / recent advances" on a research topic — and the arXiv tools (the arxiv-mcp server's arxiv tools, or the arxiv CLI) are available.
Use EasySourceFlow whenever the user provides a supported webpage, video, cloud-document link, or file for summarization. A bare supported link or attachment means "summarize this with EasySourceFlow" unless the user explicitly requests a different operation. Also use it for notes, transcription, previous results…
Cerca e recupera il testo integrale di provvedimenti di merito civile (sentenze/ordinanze/decreti di Tribunali e Corti d'Appello, dal 2016, pseudonimizzati) sulla Banca Dati di Merito pubblica del Ministero (bdp.giustizia.it), tramite il connettore manolesta. USA SEMPRE questa skill quando l'utente vuole…
Search your local Claude Code and Claude Cowork conversation history — list recent sessions, full-text search transcripts, and read full conversations stored on your own machine.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Delegate well-bounded coding tasks, resilient current web/X research, read-only investigations, code reviews, adversarial critiques, independent second opinions, approved Grok 4.5 image/video generation, and xAI TTS from Codex or Claude Code through the local Grok Build installation. Use when the user names Grok or…
Use when the user asks to find academic literature on a research question, compare scholarly evidence, trace references or citations around papers, or produce an evidence-grounded literature review from retrieved sources. Do not activate merely because an unrelated request mentions research.
MCP server "corpus-ingest-core" as configured in norton77930/corpus-ingest-core. Launched with corpus-ingest-mcp. Needs 2 environment variables to run.
★not rated 2 2d agoA
tokens not measured
originalMIT
Search local framework documentation (Svelte 5, FastAPI, Tailwind, Tauri, Next.js, Supabase) and AI Models documentation (Claude 3.7/3.5, GPT-4.5/o1/o3, Gemini 2.0/3.0, DeepSeek V3/R1, Qwen 2.5 Coder, benchmarks, pricing, routing) via agents-docs MCP before guessing API methods or hallucinating stale model knowledge.
Use when the user says deepsearch, asks for deep research, asks to investigate thoroughly, compare sources, find primary evidence, trace claims, verify current facts, synthesize scattered information, or perform multi-pass search across web, local files, GitHub, Shuiyuan, Gmail, or other available tools.
Search Entra.Chat podcast transcripts — Merill Fernando's Microsoft Entra podcast on YouTube. Runs locally from the entra-news-podcast-mcp npm package.
★not rated 2 5d agoA
tokens not measured
originalMIT
Monitor US-Iran strike probability using open-source indicators - news alerts, Iran internet connectivity, oil prices, flight traffic, military tanker detection, weather, Polymarket odds, and Pentagon activity. Use when user asks about "Iran strike probability", "strike radar", "Iran situation", "US attack Iran"…
MCP server for citation validation, formatting, and collection management. Validates DOIs, formats references in 2900+ CSL styles, manages citation collections, and catches hallucinated citations. Runs locally from the @turtletech/ookcite-mcp npm package. Needs 1 environment variable to run.
★not rated 2 3d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: