1781 Model Context Protocol servers — searchable, rated, ready to install.
130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free.
AI security scanning and trust scoring. Stack-specific threat models. Free local scan.
Explore the Claude Code CLI source — browse tools, commands, search code, and more.
Track your brand's visibility in AI search across Claude, ChatGPT, Perplexity, and Gemini.
Connect AI assistants to Roblox Studio — manipulate the DataModel with 14 tools
MCP for kie.ai: 45+ image, 70+ video, 20+ audio models with model intelligence
Create and modify GB Studio projects with MCP tools for scenes, actors, assets, and validation.
Wontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.
30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.
MCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.
OSINT MCP server — 23 tools: DNS, WHOIS, Shodan, breaches, GEOINT, crypto. Works with Claude Code.
Diagnoses ArduPilot DataFlash flight logs over the Model Context Protocol.
Access Smartschool courses, grades, assignments, and messages through the Model Context Protocol
Source-backed AI model pricing, rankings, history, and benchmark data.
Contextual guidance for AI agents in fog states. Claude-backed, Ed25519, Lightning payment.
MCP server to publish to Substack, Ghost, Dev.to, WordPress, LinkedIn + 5 more from Claude Code.
MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.
Search, cite, and read PDFs from your EndNote library in Claude Desktop
Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.
Search federal government contract opportunities from SAM.gov via Claude
Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.
Token-aware message truncation: fit a chat history into your model's context budget.
Inject, parse, and strip [N] citation markers in RAG outputs.
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
POST /mcp