3230 Model Context Protocol servers — searchable, rated, ready to install.
Model routing for AI agents: delegate bulk reads & boilerplate to cheap worker models.
Tells your agent which model to use and what it costs, across 46 providers and local runtimes.
Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Bounded readonly SHA256 verification with the official MCP SDK. No code execution or model calls.
Live Hugging Face model proofing, ATS resume scoring and career tools by Ambuj Kumar Tripathi
Create, train and publish AI chatbots for your website from Claude, ChatGPT or any MCP client.
Catches leaked credentials and PII in outbound LLM prompts
Scans RAG content/scraped pages for indirect prompt injection
Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.
Send a live, private link to a client from Claude. Updates in place, viewers by email.
Outlook / Microsoft 365 for Claude — triage mail, reply, answer invites and book meetings, confirmed
Decode a vehicle identification number into make, model, and year. No key required.
Private memory layer for AI assistants. Local-first: remember, recall, forget, expand.
A calorie MCP that looks up calories and macros from a 4M+ food catalog, not model guesses.
Several models from different labs plan in a blind proposal, debate and review loop. Your own keys.
Discover verified AI inference nodes, get the best node+model per task, pre-price chains.
Expert soccer predictions from TipMaster, since 1997: crowd groups, accuracy and model benchmark.
OpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.
Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.
MCP server for Matrix42: explore the API and data model, search the service desk, act on tickets
Code changes and unit tests by local MLX models, behind a gate a machine can run.
Juspronto connector for Claude and ChatGPT: Brazilian law-firm cases, deadlines, agenda, case files.
Guardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.
Build and publish full-stack apps from your coding agent: models, rules, pages, auth, per-app MCP.
POST /mcp