2945 Model Context Protocol servers — searchable, rated, ready to install.
Check if a website is visible to AI search (ChatGPT, Perplexity, Claude) and get per-gap fixes.
AI resume triage for recruiters. Query your candidate pool from Claude or ChatGPT.
Claude Code token usage, cost visibility, and SkillFM Beacon AI health checks for MCP agents.
Local-first portfolio tracker for overseas investors. Claude reads and writes your finances via MCP.
Ground your LLM in EU financial, crypto and AI regulation, verbatim and cited, via Compass.
Real-time Fronius inverter data in Claude — PV, battery, grid and smart meter via local Solar API.
MCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.
Score, validate, and pressure-test startup ideas with AI from Claude or any MCP agent.
Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
Agent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.
Your intent, in every AI call - every model means what you meant, not what it guessed.
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.
Read, edit, publish, and preview your pepita websites from Claude.
Structured-output enforcer: extract and validate JSON from messy LLM text.
Token-aware message truncation: fit a chat history into your model's context budget.
Access financial data and market information via Financial Modeling Prep API
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector.
Give brains to your small models. MCP server enforcing step-by-step Chain-of-Thought.
Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.
MCP server for Draw Things - local AI image generation on Mac
Query domain expiration data from domain-monitor.io via AI assistants like Claude.
PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.
POST /mcp