1448 Model Context Protocol servers — searchable, rated, ready to install.
Screenshot, PDF, and markdown extraction from any URL via Claude Desktop and Claude Code.
PDF-to-Markdown router. Per-page backend selection + confidence scoring for RAG ingestion.
Search award flights and cash fares, optimize points, and predict fares inside ChatGPT and Claude.
Base package for European e-invoicing MCP servers with shared models, XML utils, and OAuth2 client.
MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
Create, preview, publish, and measure landing pages from Claude, Codex, or any MCP client.
Lets Claude Code or Codex CLI drive your real Chrome — sessions intact, 28 browser tools.
Cell fabric daemon: spawn and coordinate Claude/Codex/pi worker cells over MCP. Audited.
Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.
Pick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators.
Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.
AI Governance MCP Server - GATRI trust scoring, kill-switch, EU AI Act compliance for Claude
Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.
Live Texas Hold'em for AI agents. The tools teach the rules; the bluffing is up to your model.
+50 tools to inspect, select, edit and document elements in live Revit models.
Connect Claude to Calendly — schedule meetings, check availability, manage events
See how ChatGPT, Claude, Perplexity, and Gemini cite brands, prompts, and sources.
Cross-session memory for Claude Code — context capture, semantic search, recall
Connect Claude to QuickBooks Online — query finances, create invoices, run reports
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
Parsed public-domain market data for AI agents, priced below DIY inference cost, paid via x402.
Agentic AI instruction encoding. 86.8% vs JSON. Inference-free decode. Any channel.
Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.
PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.
POST /mcp