MCP SAFETY LIBRARY

1,306+ validated MCP servers.

Every server screened for malicious code, prompt injection, and suspicious GitHub signals before it reaches you.

✓ VirusTotal scanned✓ Prompt injection checked✓ Dependency CVE audit✓ Network call analysis✓ 90-day revalidation
Anthropic Tool Use Guide
99
Official comprehensive guide to tool use and function calling with Claude. Best practices for buildi...
CODING✓ VALIDATED
Anthropic Claude API Guide
99
Complete guide to the Anthropic API — authentication, models, tool use and rate limits.
CODING✓ VALIDATED
Model Context Protocol Specification
99
Official MCP specification and implementation guide. Donated to Linux Foundation December 2025.
CODING✓ VALIDATED
Notion MCP Server
99
Official Notion integration. Search pages, read databases, create content, manage tasks. AgentRank #...
CODING✓ VALIDATED
Claude System Prompt Engineering Guide
99
Advanced system prompt design for Claude — personas, constraints, output formatting and tool use.
CODING✓ VALIDATED
QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard
98
QIMMA introduces a quality-focused leaderboard for evaluating Arabic language models, addressing the...
GENERAL✓ VALIDATED
New AI repo: Netflix/metaflow
98
Netflix's Metaflow is a production-grade framework for building, managing and deploying ML systems a...
MLOPS✓ VALIDATED
How to Build Your First MCP Server in 30 Minutes
98
Step-by-step tutorial for building a custom MCP server with TypeScript.
CODING✓ VALIDATED
AI evals are becoming the new compute bottleneck
98
AI evaluation processes are emerging as a critical computational bottleneck, shifting infrastructure...
GENERAL✓ VALIDATED
Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making
98
Survey on interpretable surrogate models for simulations with focus on explainable AI for decision-m...
GENERAL✓ VALIDATED
New AI repo: PaddlePaddle/FastDeploy
98
PaddlePaddle's FastDeploy offers high-performance inference optimization for large language and visi...
GENERAL✓ VALIDATED
New AI repo: FlagOpen/FlagEmbedding
98
FlagEmbedding is a high-performing embedding model optimized for retrieval and RAG applications with...
GENERAL✓ VALIDATED
New AI repo: NVIDIA-NeMo/Automodel
98
NVIDIA-NeMo/Automodel is a PyTorch distributed training library enabling efficient LLM/VLM training ...
GENERAL✓ VALIDATED
Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents
98
Ecom-RLVE introduces an adaptive verifiable environment framework for training and evaluating e-comm...
ECOMMERCE✓ VALIDATED
Algorithm Selection with Zero Domain Knowledge via Text Embeddings
98
Paper proposes using text embeddings to automatically select optimal algorithms without domain exper...
GENERAL✓ VALIDATED
MCP Security Best Practices Guide
98
How to safely deploy MCP servers. Permission scoping, OAuth patterns, prompt injection defence.
SECURITY✓ VALIDATED
Rethinking Publication: A Certification Framework for AI-Enabled Research
98
Proposes a certification framework for validating and publishing AI-generated research to ensure qua...
RESEARCH_AND_ACADEMIA✓ VALIDATED
Tool Use and Function Calling Advanced Guide
98
Advanced patterns for Claude tool use — parallel tools, tool chaining and error recovery.
CODING✓ VALIDATED
Structured Output and JSON Mode Guide
98
Extract structured data from AI responses reliably — Pydantic, JSON mode and validation.
CODING✓ VALIDATED
Morning Briefing System Prompt
98
Complete morning briefing prompt that extracts priorities from calendar, email, tasks and overnight ...
CODING✓ VALIDATED
DeepER-Med: Advancing Deep Evidence-Based Research in Medicine Through Agentic AI
98
DeepER-Med introduces an agentic AI system designed to enhance evidence-based medical research throu...
HEALTHCARE✓ VALIDATED
Claude Desktop Configuration Masterclass
98
Master claude_desktop_config.json — multiple servers, environment variables and troubleshooting.
CODING✓ VALIDATED
Site Reliability Engineering Guide
97
SRE principles — error budgets, SLOs, SLIs and toil reduction for production reliability.
CODING✓ VALIDATED
Research Synthesis Prompt Framework
97
Read multiple sources, extract key claims, identify conflicts and produce a coherent sourced synthes...
RESEARCH✓ VALIDATED
Few-Shot Prompting Mastery Guide
97
Advanced few-shot prompting techniques — example selection, format consistency and edge case coverag...
CODING✓ VALIDATED
Inbox Zero Triage Prompt Pack
97
6-prompt system for reading, categorising, actioning and clearing an email inbox at scale.
CODING✓ VALIDATED
Claude Haiku vs Sonnet vs Opus Guide
97
When to use each Claude model tier — cost, capability and latency tradeoffs.
CODING✓ VALIDATED
Stripe MCP Server
97
Official Stripe integration. Query customers, subscriptions, invoices, payments, refunds.
FINANCE✓ VALIDATED
New AI repo: ParisNeo/lollms-webui
96
Open-source web UI for running large language and multimodal models locally with 4.7K GitHub stars.
GENERAL✓ VALIDATED
Building a Fast Multilingual OCR Model with Synthetic Data
96
Hugging Face demonstrates building efficient multilingual OCR models using synthetic data, reducing ...
GENERAL✓ VALIDATED
New AI repo: modelscope/evalscope
96
ModelScope's EvalScope provides a customizable framework for benchmarking LLMs, VLMs, and AIGC model...
GENERAL✓ VALIDATED
New AI repo: vllm-project/vllm-ascend
96
Community-developed hardware acceleration plugin enabling vLLM inference optimization on Ascend proc...
GENERAL✓ VALIDATED
Exploration and Exploitation Errors Are Measurable for Language Model Agents
96
Research demonstrating measurable frameworks for quantifying exploration-exploitation trade-offs in ...
GENERAL✓ VALIDATED
Evaluating Strategic Reasoning in Forecasting Agents
96
Research on strategic reasoning capabilities in forecasting agents that may improve prediction accur...
GENERAL✓ VALIDATED
New AI repo: Tongyi-MAI/MobileWorld
96
MobileWorld is a benchmarking framework for autonomous mobile agents in interactive environments wit...
GENERAL✓ VALIDATED
New AI repo: Haozhe-Xing/agent_learning
96
Comprehensive AI Agent development tutorial repository with daily arXiv paper tracking, covering fou...
GENERAL✓ VALIDATED
New AI repo: inclusionAI/AReaL
96
AReaL provides a simplified RL framework for integrating reinforcement learning with LLM-based agent...
GENERAL✓ VALIDATED
Prompt Injection Defence Guide
96
How to protect AI agents from prompt injection attacks in production systems.
SECURITY✓ VALIDATED
New AI repo: run-llama/ParseBench
96
ParseBench is a document parsing benchmark designed to evaluate AI agent performance on extraction a...
GENERAL✓ VALIDATED
New AI repo: MemMachine/MemMachine
96
MemMachine provides a universal memory layer for AI agents, enabling scalable and interoperable stat...
AI_AGENTS✓ VALIDATED
New AI repo: MemoriLabs/Memori
96
Memori provides LLM-agnostic memory infrastructure that persists agent execution and conversations a...
AI_AGENTS✓ VALIDATED
Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs
96
Waypoint-1.5 enables creation of interactive 3D worlds on consumer-grade GPUs, expanding accessibili...
GENERAL✓ VALIDATED
New AI repo: googleapis/mcp-toolbox
96
Google releases MCP Toolbox for Databases, an open-source Model Context Protocol server enabling AI ...
DEVELOPER_TOOLS✓ VALIDATED
New AI repo: Anionex/banana-slides
96
AI-native PPT generator enabling template-free slide creation from text, outlines, or voice commands...
PRODUCTIVITY✓ VALIDATED
New AI repo: Lin-jun-xiang/agent-line-bot
96
Open-source AI agent for LINE messaging platform with integrated web search, image generation, and v...
GENERAL✓ VALIDATED
New AI repo: OpenHands/OpenHands
96
OpenHands is an AI-driven development platform enabling autonomous software engineering and developm...
DEVELOPER_TOOLS✓ VALIDATED
Learning Accelerator Prompt Pack
96
Spaced repetition, Socratic method, concept explanation and knowledge testing for rapid skill acquis...
EDUCATION✓ VALIDATED
New AI repo: fim-ai/fim-one
96
LLM-powered agent runtime enabling dynamic DAG planning and concurrent execution for complex workflo...
GENERAL✓ VALIDATED
1 / 28NEXT →
GET ACCESS

Full library access + 35 shortcuts + AI cost routing.

Browse freely. To use these servers in your workflow with safety scores and routing, subscribe to Followloop.

START FOR $5/MONTH →

30-day money-back guarantee · cancel anytime