搜索「3D Models」的结果

dev.rostro/rostro

Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.

gliana-ai

vlatest

io.smithery.glianalabs.gliana-ai

Pay-per-call generative AI — 60+ models (image, video, music, speech). No signup, no API key; pay per call from your wallet over MPP/x402.

//beforeyouship — LLM cost modeling from your editor

vlatest

io.smithery.beforeyouship.cost-model

Model the realistic monthly cost of an LLM app **before you build it**. Not a token calculator: retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth are modeled in, across GPT-5.x, Claude, Gemini, DeepSeek, and more. **Works without a key.** Connect and ask — demo mode covers the six free-tier models. A Pro API key ([beforeyouship.dev](https://beforeyouship.dev)) unlocks the full 18-model catalog. ## Tools | Tool | What it does | |---|---| - **`estimate_cost`** Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case $/mo per model, growth scenarios, and an opinionated recommendation. | - **`get_model_prices`** Current per-1M-token pricing (input, output, cached, batch) with context windows and staleness metadata. | - **`list_archetypes`** Seven preset architecture patterns (chatbot, RAG pipeline, multi-step agent, …) used as starting points for estimates. | ## Try it Paste into Claude Code or Cursor after connecting: > Estimate the monthl

Dynamic Feed

vlatest

io.smithery.samimeshkor.dynamic-feed

Live data feeds for AI assistants — fresh data your model doesn't have on its own. Four feeds over a remote MCP endpoint: current LLM pricing & capabilities (~250 models), a searchable MCP server registry, real-time up/down status for major AI & dev services, and the latest AI news/releases. Free tier available.

protein-mcp-server

vlatest

io.smithery.cyanheads.protein-mcp-server

Federated protein structure & annotation across experimental (PDB) and predicted (AlphaFold) models.

io.smithery.DeniseLewis200081.rail

Provide a simple API interface to search and filter 12306 train tickets, including direct, transfer, and stopover queries. Enable large language models to access real-time 12306 ticket information efficiently. Enhance user experience by integrating comprehensive train ticket search capabilities.

epl-mcp

vlatest

io.smithery.abneesh.epl-mcp

# EPL Language MCP Server The official Model Context Protocol (MCP) server for the EPL (English Programming Language) ecosystem. This server provides AI coding assistants with direct access to the EPL runtime, compiler, and documentation. It empowers AI models to securely run EPL code, execute test suites, analyze Abstract Syntax Trees (ASTs), and fetch real-time syntax documentation. **Key Capabilities:** - **Code Execution:** Run EPL scripts dynamically and return standard output and errors. - **AST Generation:** Parse EPL source code into structural JSON trees for deep analysis. - **Documentation Retrieval:** Fetch the latest EPL language rules and standard library documentation. - **Test Harness:** Run and evaluate EPL test suites programmatically.

Meteomatics

vlatest

io.smithery.meteomatics.meteomatics

The Meteomatics MCP (Model Context Protocol) server allows AI agents to securely access Meteomatics weather data tools. MCP is an open standard that lets AI applications connect to external tools and data sources. With the Meteomatics MCP, agents can request weather data directly from the Meteomatics API through a secure /mcp endpoint. The MCP server manages authentication using OAuth (client registration, authorization code + PKCE, and refresh tokens). Once connected, the AI agent can access data, models, parameters, time ranges that are available to your Meteomatics API account.

Hugging Face

vlatest

io.smithery.huggingface

AI model hub for machine learning. Discover models, explore datasets, and access model documentation and capabilities.

GoCreative Agent API

vlatest

io.smithery.colinhughes2005.gocreative

**Pay-per-call intelligence for AI agents — no API key, no signup.** A 17-model frontier **LLM gateway** (GPT-5, Claude 4.5 Sonnet, Claude Opus 4.6, Gemini 3 Pro, DeepSeek V3.1, and more) plus **350+ data, compliance & enrichment tools** — sanctions/KYB screening, SEC filings, crypto markets, company & domain intelligence, and lead research. Agents pay **per call in USDC on Base** via the x402 protocol. No accounts. No keys. No subscriptions. **Highlights** - 🧠 LLM gateway: `ai/ask` ($0.02) · `ai/pro` ($0.08) · `ai/ultra` ($0.25) — pick any model, pay USDC - 🛡️ KYB-360 — sanctions + PEP + risk + registry + firmographics in one call - 🔎 Sanctions screening: OFAC / EU / UK / UN + 100+ lists - 📈 SEC financials, crypto market data, company & domain intel - 💸 357 tools, all pay-per-call USDC on Base Live API: https://api.gocreativeai.com · Free model catalog: https://api.gocreativeai.com/v1/ai/models

ham.run

vlatest

io.smithery.hamrun.hamrun

Open-source marathon physiology calculators for endurance runners. 12 tools: race time prediction (Riegel model), pacing strategy, fueling plans, running economy analysis, caffeine protocols, heat acclimation planning, periodization comparison, and grade-adjusted pace. Strava-connected tools for training load and activity analysis. All models are citation-backed from peer-reviewed exercise physiology research. Stateless tools work without authentication at ham.run.

io.smithery.hi-10f9.vetted-consumer

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.

SportIQ

vlatest

io.smithery.utkarshgupta885.sportiq

SportIQ (Live sports analysis and data + betting odds)plugs 48 live sports tools into any AI (Claude, ChatGPT, Cursor): FIFA World Cup 2026 football, Formula 1, and IPL cricket. Ask in plain English — it simulates brackets, finds value bets, optimizes Dream11 teams, and models F1 pit strategy. Free, open-source, installs in seconds via uvx.

io.smithery.XJTLUmedia.x23

AI Answer Copier is a Model Context Protocol (MCP) server that solves the "Final Mile" friction in educational content creation. It enables AI models to move beyond just writing questions to actually generating the files required for teaching and assessment. By functioning as a native MCP server, this tool allows Claude or any MCP-enabled IDE to directly pipe its output into specialized educational formats. No more manually fixing bullet points in Word or wrestling with CSV headers for your LMS. Key Capabilities:Zero-Friction Pipeline: Your AI can now "see" your local export tools. Ask it to: "Generate 10 biology questions and send them directly to my Quizizz CSV." Multi-Format Exporting: Seamlessly convert AI responses into upload-ready files for Kahoot, Quizizz, Canvas (JSON), Moodle (XML), and professionally formatted PDFs. Intelligent Smart-Parse: Automatically identifies question stems, multiple-choice distractors, and correct answer keys from raw AI text. First-Class Math & Code: Native support for

Promptibus MCP

vlatest

io.smithery.promptibus.mcp

Model intelligence for AI agents — syntax, parameters, pricing, and routing for 67+ generative AI models (Midjourney, Flux, Suno, Runway, DALL-E, Stable Diffusion). 7 tools for any MCP client.

Share of Model

vlatest

io.smithery.scrappycmo.share-of-model

Track how often AI models mention and recommend your brand. Probe GPT-4o, Claude, Gemini, and Perplexity to measure your Share of Model - mention rate, position quality, and competitive ranking. Essential for any brand in the era where AI agents influence purchasing decisions. **4 tools:** - `generate_som_report` - full analysis in one call - `probe_ai_models` - raw probe data across models - `compare_competitors` - head-to-head leaderboard - `calculate_share_of_model` - pure metrics from probe data **BYOK** - bring your own API keys. Only pay for what you probe.

Gemini File Search

vlatest

io.smithery.node2flow.gemini-file-search-rag

MCP server for Google's Gemini File Search and RAG (Retrieval-Augmented Generation). ## Features - Create and manage File Search stores - Upload documents (text, PDF, base64) with custom metadata and chunking config - Import existing Gemini files into stores - Track upload/operation status - Query documents using RAG with model selection and metadata filtering ## 12 Tools **Store Management**: create, list, get, delete stores **Upload & Import**: upload content directly or import existing files **Operations**: check status of store/upload operations **Documents**: list, get, delete documents in stores **RAG Query**: query documents with Gemini models (supports metadata filters) ## Configuration - GEMINI_API_KEY — Get one at https://aistudio.google.com/apikey

Muapi

vlatest

io.smithery.am-1m1k.muapi

Access 400+ generative AI models directly from your AI assistant. Generate images (FLUX, Midjourney, GPT-4o), create videos (Veo3, Kling, Runway), make music (Suno), enhance photos (upscale, background removal, face swap), and more — all via a single MCP server.

ai.truverif/panel-review

Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.

com.merofoundry/merofoundry

Build and publish full-stack apps from your coding agent: models, rules, pages, auth, per-app MCP.

com.rendobar/mcp

Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.

io.github.huangjunsong404-crypto/china-nmpa-udi

Structured China NMPA UDI data for AI agents: devices, registrants, models and registration numbers.

com.picsart.api/gen-ai

Generate and edit images, videos, and audio with 150+ models from 20+ vendors.

io.github.MichaelCrowe11/crowe-logic

CroweLM tiers and frontier engines by name, metered per Crowe Logic plan. Ask, list models, account.