MCP Server Directory

The Cure Protocol com.negativeresistance/cure-protocol

Agent research API for 15 disease areas, plus a T1D cure lab, sourced evidence ledger and models.

Epoch Ai Models io.github.pipeworx-io/epoch-ai-models

Epoch AI — AI models database

Kourier sh.kourier/info

Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.

AI Video Atlas com.aivideoatlas/atlas

Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.

Give LLM agents webcam access: capture photos and record short videos over MCP.

Parse gun and ammo titles (model, caliber, cost per round); find GunsNPrices price comparison pages

Tastepix io.github.paablobello/tastepix

12 image models (Nano Banana, GPT Image, FLUX…) and 10 tools in chat. No API keys. Pay per image.

Agent Docs io.github.KonstantinStarovoytov/agent-docs

Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily.

Vela Breakout partners.vela.breakout/breakout

What's growing in tech, measured daily: AI apps, models, dev tools, software spend, hiring.

Airtable MCP by InsightfulPipe com.insightfulpipe/airtable

Hosted Airtable MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

A browser your AI agent remembers. Learn a site once, replay it in one call, zero model calls.

The modeler's client for SDCStudio: search the catalog, estimate, assemble and publish SDC4 models.

Use This Skill com.usethisskill/skills

Search 1,700+ agent skills for Claude, Codex and Cursor, each safety-scanned, with proofs.

Formy il.co.formy/formy

Read your Formy forms and responses over OAuth. For Claude, ChatGPT, Cursor and VS Code.

Mode VC Chart: Chinese AI Models vs. US Models: How Close Is China? com.modevc/chart-chinese-ai-models-vs-us-models

qwen3.8-max trails claude-fable-5.1-max by 27 points. Over the past year the gap has stayed.

Bria com.bria-api/bria-mcp

Commercially licensed image generation and editing with IP indemnification.

AI usage limits (Claude Code, Codex, Copilot, Windsurf): check budget and time until reset.

Mode VC Chart: Best AI Model vs. Most Popular AI Chatbot com.modevc/chart-best-ai-model-vs-most-popular-ai-chatbot

Anthropic builds 14 of the Arena's top 50 models and OpenAI builds 5. But 44% of US adults use.

Firemark AI com.tryfiremark/firemark

Read how often ChatGPT, Perplexity, Gemini and Google AI name your brand, its rivals and sources.

AgentGid com.agentgid/agentgid

Live data on AI agents, APIs and models: prices, free tiers, limits, outages, real-world usage.

RenRaku jp.co.renraku/renraku

メールと LINE 公式アカウントの顧客対応サービス RenRaku を、Claude や ChatGPT などの AI から利用するための MCP サーバーです。

Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

Search, read and grow a Karpathy-style LLM wiki of linked Markdown pages, with cited answers.

Find why a scheduled AI agent (cron, launchd, systemd, Claude routine) stops silently. Read-only.