3230 Model Context Protocol servers — searchable, rated, ready to install.
Model Context Protocol server for the DocAuto document-generation API.
Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.
Track your brand's share of voice in ChatGPT, Claude, Perplexity and Gemini. Pay per check.
12 free tools: PDF, OCR, QR codes, audio transcription, URL scraping, Excel, Word. No key needed.
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
Local-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.
Unified MCP Hub for managing multiple Model Context Protocol servers
AI text detection and humanization for Claude Code, Cursor, and Windsurf.
Inject, parse, and strip [N] citation markers in RAG outputs.
Give brains to your small models. MCP server enforcing step-by-step Chain-of-Thought.
Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.
Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.
OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
MCP server for 1C:Enterprise — read+write CRM/ERP through Claude/Cursor/Cline.
The Global Price Benchmark for AI Inference. 1,600+ SKUs, 40+ vendors, 14 price indexes.
Apple Health data for Claude, Cursor, and any MCP client — 100% local on your Mac.
Generate and edit images and video via OpenRouter or any OpenAI-compatible API.
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
Normalize AGENTS.md / CLAUDE.md / .cursor/rules / .clinerules / .windsurf/rules from one source.
Connect Claude, Cursor, or ChatGPT to your business data. Ask questions, get answers.
Agent tracing, cost tracking, anomaly detection for LLM agents
Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
POST /mcp