3359 Model Context Protocol servers — searchable, rated, ready to install.
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.
Plan agent workload routes from evaluation and cost data. $1 USDC per plan; modeled savings only.
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Find and remove the writing patterns a profile lists. Deterministic rules, model rewrite opt-in.
Korean cloud for AI agents — servers, Docker apps with HTTPS, domains, scraping, 300+ AI models
Track job applications on a board: let Claude or ChatGPT read and update jobs, interviews, notes.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
MCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.
How a brand shows up in ChatGPT, Claude, Gemini and Perplexity answers.
Create, launch, and manage Meta + Google ads from Claude and ChatGPT.
Manage SysML2 projects; check, evaluate, verify, query, document and diagram models.
Customer support for MCP servers: work your tickets from Claude or any MCP client. Service key auth.
Drive FreeCAD from an agent: CAD modeling, drawings, FEM, CFD, EM, and multiphysics simulation.
Calm day planner for designers and freelancers. Read, add, time and move your tasks from Claude.
A coding and development harness on local models or hosted APIs, for code, review, research and ops.
Test FIX from Claude, ChatGPT, or Cursor: free sandbox FIX sessions or your own FIXSIM instances.
Hand-verified AI infrastructure directory: tools, alternatives, EU providers, LLM API prices.
MCP server for Matrix42: explore the API and data model, search the service desk, act on tickets
Trust verdicts on repos, models, VS Code and Docker Desktop extensions and agent skills.
AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…
Consult Grok through xAI's metered API with exact model selection and no fallback
Second opinion for agents: 3-4 AI models answer, one verdict with confidence and dissent.
POST /mcp