3181 Model Context Protocol servers — searchable, rated, ready to install.
Make AI-drawn video from chat: your LLM draws every frame in code; add narration, music and SFX.
Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.
Meta Ads and Google Ads MCP server: 250+ tools for Claude, ChatGPT, Cursor and Codex.
Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.
Company social handles (LinkedIn, Instagram, X, Facebook, YouTube) via Apify MCP.
AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.
Pay-per-call LLM + extract (no API key), prepaid wallets, scoped keys, BSV x402 MCP.
Run fal.ai models, poll the inference queue and read model schemas.
Consistent prompts for one human character across image and video models. Paid per call, x402.
CroweLM tiers and frontier engines by name, metered per Crowe Logic plan. Ask, list models, account.
500+ AI models in one account: find and price models, make images, video, speech and text.
Connect Claude or Cursor to books, invoices, bills, payroll, and sealed closes.
What Claude, ChatGPT, Cursor and the MCP Registry require to list an MCP connector or plugin.
Track your brand in AI answers: ChatGPT, Gemini, Claude, AI Overviews. Also a ChatGPT plugin.
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
Versioned scientific models with units and SBML, CellML, Modelica export.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Robot embodied-AI cloud for GPU training, inference, benchmarks, and robot data collection.
Every EmpirioLabs model and platform feature as tools: chat, media, search, jobs, GPU Cloud, agents.
GuestGraph: One guest, not five strangers
Enforce AI budgets before the model call and track cost per customer across 10 providers.
Manage turbopress hosting from Claude or ChatGPT: site health, domains, mail, SSL and AI Launch.
Ask the human for API keys in a browser page and write them to .env. The model only sees key names.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
POST /mcp