"Understanding local computer vision models like YOLO" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
mumo is a remote MCP server for multi-model deliberation. Your agent sends a question to models from different labs — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more — and gets back their full responses plus typed cross-model reactions. The participating models react to each other directly and explain, in their own words, what they agree with, challenge, or want to explore further. Agents can run a deliberation with `create_deliberation`, wait for results with `wait_for_round`, and steer follow-up rounds with `append_round` using structured signals like KEEP, EXPLORE, CHALLENGE, CORE, and SHIFT. Built for architecture, plan/spec review, strategy, and pre-launch pressure tests. Free tier available. API key required.
Hubris is an OpenAI-compatible LLM gateway for the Russian market, billed in rubles. This MCP server gives agents access to the model catalog (400+ models with ruble pricing), account balance, and chat completions with full parity to POST /v1/chat/completions. Tools: models_list, models_search (filter by capability/price/context length), models_get_pricing, balance_get, chat_complete. Resources: hubris://catalog/models, hubris://docs/quickstart. Prompt: compare-models. Docs: https://hubris.pw/
One MCP server for top AI models and live data. Images (Nano Banana, GPT Image, FLUX, Seedream), video (Veo, Kling, Seedance, Runway), voice and music (ElevenLabs, Lyria), plus Google, Maps, YouTube, LinkedIn, Amazon, social and public data. Seven tools: search_tools and get_tool (free) find a tool and show its inputs and price, run_tool runs it, list_calls, get_call and get_balance show your call history, any one call and your balance, upload_file (free) sends input files up to 100 MB (photos, voice tracks, video) with no hosting needed. Each run has a fixed price, charged only when it returns a usable result. Calls finish inside their request (no cancelling needed); get_call recovers a dropped one. Pay per call with x402 (USDC on Base) or an account API key. Prefer one MCP tool per model? Use https://tollnode.com/mcp/full.
Make images, video, music and voiceovers with more than 1,000 generation models.
Official hosted MCP server for Wiro AI. Run 1,000+ image, video, audio and LLM models, build and run workflows that chain them, and deploy and talk to AI agents from any MCP client.
Multi-provider AI OCR and structured JSON/table extraction MCP server (https://smartocr.dev). Extract strict custom JSON schemas, Markdown tables, and CSV rows from PDFs, invoices, bank statements, receipts, timesheets, and scanned images using intelligent routing across Native PDF, Google Cloud Vision, and AWS Textract. Works out-of-the-box on the free tier (2 free documents/day) or with a Smart OCR API key (10 free credits on signup at smartocr.dev).
Which LLM should I use for this task? Ask in plain words and get the models that score best on the matching benchmark board, within your price, context window and open-weights limits. Covers 400+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, Mistral and more, with benchmark scores (coding, agentic, reasoning, math, knowledge, design) and API list prices per million tokens, updated daily. Tools: recommend_model, get_leaderboard, compare_models, get_model, get_prices, list_categories. Free, no API key, data under CC BY 4.0. Docs: https://llmbenchmark.ai/api
Generate images, video, speech, music and text with HiAPI's AI models. OAuth or API key.
OpenAny is the B2A (business to agent) marketplace. Add one MCP endpoint, https://mcp.openany.si, and your agent can find and use 3,200+ APIs and 168+ AI models. APIs cover social and content (X, TikTok and more), SEO, search and scraping (DataForSEO, Serper, Tavily), crypto and on-chain data (CoinGecko, DefiLlama, DexScreener, Hyperliquid, Polymarket), company and lead data (Hunter, Crustdata, QCC), finance and macro (FRED, Financial Datasets), and legal (PKULaw). Models include chat and reasoning (GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax), image (Midjourney, FLUX, Nano Banana, Seedream, GPT Image), video (Veo, Kling, Seedance, Hailuo, Wan) and audio. Searching and checking prices is free with no key. You only need an OpenAny API key to run a call, and you pay per call.
Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.
Official AI/ML API server: 10,000+ AI tools and models for chat, image, video, audio, search, data.
Generate video, images, music, voiceovers, captions and dubbing with 40+ AI models.
Live prices for 111 Chinese models; batch cost calculators for video and images.
Look up medical AI datasets and open models: verified licenses, evidence and access details.
Local LLM serving setup audit: a deliverable delivered per API call as an independent atom service.
AI video, image and audio generation with 140+ AI models from any MCP agent
Read-only HopBase AI gateway tools: models, limits, docs search, balance and usage for your API key.
Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.
Generate and upscale AI images, video and audio with leading models, right from your AI chat.
Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.
Generate and edit images, video, audio and 3D with fal. Discover models and check prices.
Connect CNAPS Studio to Claude or ChatGPT, then just say what you want. "Upscale this photo 4x" or "remove the background and make it a short video". It picks the models, builds the flow, runs it, and gives you the file back in the same chat. 80+ AI models and 80+ tools for image, video and audio. Sign in with your CNAPS account (OAuth), no API key needed. n8n and Zapier work too. Setup guide: https://docs.cnaps.ai/ai-assistant
Video, images, voice, music. 78 models at list price, zero markup. Daily cap. Failed renders free.
Account-less MCP access to 45 Gemini models & autonomous agents via L402, x402, and MPP.
Generate images, video and audio from 120+ AI models, plus lipsync, headshot and cast-swap studios.
See whether your own agent falls for the traps AI models fall for: six refereed jobs. No account.
Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.
Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.
Search 10k+ free CC0 3D models by meaning/size; generate and remesh from chat.
Score text 0 to 100 for chatbot habits like filler, em dashes and buzzwords, each one marked.
Generate and edit images, upscale photos, remove backgrounds, and create videos with Fotor. Discover available AI models and supported parameters, and upload images, videos, and audio for supported workflows.
EasyGerber brings AI printed circuit board (PCB) design, layout, and routing to MCP-compatible assistants. Describe a circuit or start from firmware pin assignments, search published electronic components, and build schematics using catalog parts with their footprints and available 3D models. Create and revise boards, generate layouts with automatic component placement and routing, inspect previews, and check saved layouts for blocking design issues. Export manufacturing ZIPs containing Gerber and drill files, a bill of materials, and component placement data, or download an editable EasyGerber (.egb) file. Start without signing up. Your agent uses one private board reference to create and continue a board, including catalog access, edits, layout, checks, previews, and exports, without a separate guest setup step or token to manage. To keep the board in your account or work with permitted saved personal or organization boards, complete EasyGerber sign-in and OAuth consent, then resume the same task. Account permissions, plan limits, and generation billing apply; support depends on your MCP client and installed integration.
Cloud-native, serverless Model Context Protocol (MCP) server using Streamable HTTP (https://brightcanoe.com/api/mcp) that enables AI agents like Claude and Cursor to check live calendar availability, create appointments, search Client 360 CRM records, and retrieve 24/7 AI voice receptionist call logs.
Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
Calibrated vision for AI agents: meal nutrition estimates, personal color analysis, an integrated styling profile and client-ready PDF style reports, with a free photo pre-check. x402 (USDC on Base), no API key; failed calls are never charged.
Paste a draft and see the habits that make writing read like it came from an AI model.
Ask other AI models and generate images, speech, music and video from your coding agent.
Rent A100 and H100 GPUs by the minute from your agent, within a spending limit you set.
Generate AI images, video, and audio with many frontier models, private by default.
A moodboard from a creative brief: five distinct visual directions, each rendered by two image models, for brand, interior, fashion or project direction. Returned as square images.
500+ AI models in one account: find and price models, make images, video, speech and text.
Search what the founders, CEOs and researchers building AI said in long podcast and YouTube interviews. Each result is a moment of a few minutes with the speaker, what they do, the show, the date, their quote and the page to cite, and one tool says how builders answer big questions like "Is AI a bubble?". Read-only, no sign-in, free.
Benchmark your own prompt on 100+ models with real API calls, then choose the winner by accuracy, cost, speed, or any mix of those.
Ask Drex decision models typed questions about a state and get calibrated probabilities; free within per-network limits.
ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work. Keyed remote MCP server (x-api-key).
Create video, images and audio from your AI assistant: ad templates, 20 one-photo video effects and 70+ models. Every job is priced first.
Search, rank, and compare 500,000+ AI models, datasets, papers from 13+ platforms. Hardware-aware model selection with VRAM and license constraints. 5 tools: search, rank, explain, select_model, compare.
Generate AI video, images, music and sound effects from any agent with Seedance 2.5, Veo 3.1, Kling 3.0, Nano Banana Pro, GPT Image 2.5 and 20+ models. OAuth sign-in, no API key, 100 free credits.
Discover AI models and their input schemas, generate images, videos, music and speech, create or clone voices, and check generation status through APIXO. Public tool discovery is available without sign-in. Account-specific and generation operations require authentication; generation uses APIXO credits. Website: https://apixo.ai
Generate images and videos with frontier AI models. Pay per use; credits never expire.
AI video, images, music & SFX: Seedance 2.5, Veo 3.1, Kling 3.0, Nano Banana Pro, 20+ models.
Typed-question decisions from Jev: classify, moderate, route models and guard tool calls.
Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.
Use your own trained text and picture classification models from any AI assistant.
Official Langfuse documentation for building LLM evaluation workflows: datasets, experiments, LLM-as-a-judge evaluators, custom scores, human annotation, and prompt/model comparison. Search documentation and retrieve current code examples, including tracing and SDK integrations. Remote Streamable HTTP server; no account, API key, or local installation required. Provides documentation guidance; accessing project data and running evaluations require separate setup.
Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.
Publish to Instagram from your AI assistant. Pith lets you publish your own images and captions, review and approve AI-generated drafts, rewrite captions, manage scheduled posts and update your brand voice through MCP. Supports stories, feed posts and carousels. Hosted Streamable HTTP endpoint with browser-based sign-in; no local installation or API key required. Publishing your own content is free; AI-generated content follows plan limits. Setup and documentation: https://pith.day/connect/mcp
Publish the apps you build with AI and share them like a Google Doc, with data, files and AI.
Deterministic Music Theory for Claude, Cursor, and Autonomous AI Agents Large Language Models (LLMs) frequently hallucinate music theory, leading to incorrect notes, false Roman numerals, and broken voice leading. THIRI solves this by providing a deterministic, mathematical music-theory engine (pitch-class-set theory over ℤ/12) directly to your AI. It gives AI assistants precise, reproducible harmonic reasoning in milliseconds, allowing them to write correct musical scores, analyze progression
AI research intelligence for AI, ML, NLP, vision and robotics with citations and entity graphs.