新着スキル

A free, hosted MCP server for local-LLM hardware decisions. Ask whether a model fits your GPU, Mac, or mini-PC, which GGUF quant to download, the cheapest machine that runs it, and the buy-vs-rent-vs-API cost, from a maintained catalog of models and machines plus a monthly used-GPU price feed. No install, no API key. Tools: can_i_run_it, recommend_quant, cheapest_hardware_for_model, recommend_hardware, compare_hardware, cost_compare, get_used_gpu_prices, list_models, list_hardware. Works with Claude, Cursor, Cline, and any MCP client.

The MCP directory that vets servers, not just lists them. Search by task, then get an advisory screen on a server before your agent calls its tools: whether each tool does what it claims, backed by conformance monitoring and a public drift ledger. Advisory (REVIEW / UNVERIFIED), monitored not enforced, not a safety verdict.

Query the world's robot directory - 812 robots across 30 categories and 319 brands. Tools: search_robots (by category, brand, price, use case), get_robot and get_robot_full (complete specs), compare_robots (side-by-side diff), get_category, and get_job_automation_risk (robot displacement scores for 240+ professions - data available nowhere else). All reads public, no auth.

Use the SAP MCP Wizard or install the library from the npm registry to automatically create and configure a Solana/SAP wallet via https://mcp.sap.oobeprotocol.ai

Barcode lookup, nutrition search, and product comparison for 3M+ crowd-sourced food products.

Query FDA data on drugs, food, devices, and recalls via openFDA. STDIO or Streamable HTTP.

Global weather via Open-Meteo: forecast, ERA5 archive, marine, air quality, geocoding, elevation.

Search and audit NIST NVD CVEs by keyword, severity, CWE, CISA KEV status, and CPE.

Query U.S. Census Bureau data, variables, and geography via MCP.

Search Wikipedia, read summaries and full text, target sections, find nearby pages, list languages.

Create long-form (faceless YouTube) videos end to end from any MCP client: script, locked character references, storyboard, voiceover, and final video editing — with characters and style held consistent across every shot. Making long-form AI video today means 8+ tabs stitched by hand — an LLM for the script, a voice model, an image model, a video model — with characters drifting between tools and style resetting at every export. Framesail replaces the patchwork: the whole pipeline runs in one place and manages your video's context end to end. Six stages: Style (paste images, videos, or YouTube links and Framesail reverse-engineers the look, voice, and direction), Script (write it yourself or generate it in your narrative style), Reference images (auto-generated for every character, place, and prop), Voiceover (one narrator or many characters, with word-level timing), Storyboard (planned scene by scene), and Editor (captions, music, SFX, then export). No black box: you control every prompt, asset, model, and setting.

Give any AI agent a shopping brain. LMK.today is an open Model Context Protocol server with curated cross-merchant search, real price history, live demand signals, and editorial gift collections — no account required. More at https://lmk.today/mcp

Live global-intelligence data as a 39-tool MCP server: real-time markets, conflict events, country risk and resilience scores, shipping chokepoints, maritime and aviation activity, energy, climate, health, cyber threats, sanctions, forecasts, and AI-generated world/country briefs. Discovery is anonymous — connect and issue tools/list with no key. Every tool supports JMESPath projection so agents fetch exactly the fields they need. Data calls use OAuth2 or an API key from worldmonitor.app/pro.

Quantitative crypto backtesting & Bitcoin market-regime analytics. 73 MCP tools: honest look-ahead-aware backtest validation with Deflated-Sharpe-Ratio correction, point-in-time 10-indicator Bitcoin cycle scoring, macro-regime composites, Edge-Library filter effects, 22 on-chain BRK series (since 2009), altcoin screener, sentiment, "buy now or wait?" decision-math, conditional historical-analog base rates & live subscriptions. Core outputs are not reproducible from public OHLCV/market-data APIs. Covers crypto plus stocks/ETFs/commodities/forex. Free tier, no credit card.

Read-only MCP server for verified book recommendations and reading lists. Ask who recommends a book, what books a public figure recommends, consensus best-of lists, series reading orders, and book summaries. No authentication required.

Listen to Sadhu exposes a searchable corpus of Vedic scripture and recorded lectures. Look up verses by reference (e.g. "BG 2.13", "SB 5.5.3", "CC Madhya 8.128") with original Devanagari/Bengali, IAST transliteration and translations; read commentaries, prose chapters and letters; and search transcribed talks with semantic + lexical retrieval. Inline audio/video players let you hear a lecture passage or watch a clip. Read-only, no auth, no writes.

Verified business-identity intelligence for AI agents & MCP clients — company verification, VAT, BORME, GLEIF, ownership and risk signals across 10 countries. 11.3M verified entities and 40.3M BORME acts. Remote MCP server, free tier (100 req/month). Sources: BORME, VIES, GLEIF, Wikidata.

Real SEC, 13F, insider, congress & macro data your AI agent can cite. 24 tools — institutional 13F holdings (85M+ rows), insider & congress trades, spot-Bitcoin-ETF ownership, company financials, and Treasury/Fed/BLS macro series. Every answer traces back to the original SEC filing. Free tier: 200 calls/day.