2449 Model Context Protocol servers — searchable, rated, ready to install.
Redact PII from text before it reaches a model. Nothing stored, no third-party AI.
Build, edit and publish websites from Claude, ChatGPT, Cursor and Gemini. No code — Zarla hosts it.
Explore discoveries, ask questions, share findings, and build collaborations with other agents.
Generate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.
Enforce AI budgets before the model call and track cost per customer across 10 providers.
Django admin models over MCP: CRUD, actions, history, autocomplete — capped by Django permissions.
Reads .mcp.json / .vscode/mcp.json / claude_desktop_config.json while you edit it and marks the line
Create, edit, render, save, and export voxel models with interactive 3D previews.
Your own closet in your AI: outfits from clothes you own, rendered on a model inline.
Korean cloud for AI agents — create servers, deploy Docker apps, manage domains, call 300+ AI models
MCP server that lets image-only models look at video: timecoded frames, measurable properties.
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.
Which Python library APIs changed after your model's training cutoff (static diff, no model calls)
Your audit methodology inside Claude: findings, risks, controls and workpapers in your team format.
Recherche de téléfilms de Noël et de leurs diffusions TV, en lecture seule, horaires Europe/Paris.
Alerts on breaking changes, deprecations, and pricing shifts across major LLM provider APIs.
Build, version and render resumes as PDFs from Claude or any MCP client.
Test FIX from Claude, ChatGPT, or Cursor: free sandbox FIX sessions or your own FIXSIM instances.
Dead-man's switch for Anthropic API spend: kills the key the instant it crosses a limit you set.
Repairs malformed JSON from LLM output, validated against a schema. Paid per call via Stripe.
Autonomous coding pipeline: frontier models plan and review, a local model implements, gated by TDD.
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
Interface observations and explicit GOMS/KLM, Fitts, Hick–Hyman and cognitive walkthrough models.
POST /mcp