MCP Server Directory

LooperTask com.loopertask/loopertask

AI-native Kanban board — connect Claude to claim, work and move your tasks over MCP.

Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.

Docs + source RAG for Pipe language: semantic search, cited answers, code symbol lookup.

Aurentia fr.aurentia/mcp-server

Your Aurentia workspace — projects, CRM, tasks, deliverables — in Claude, Cursor or any MCP client.

Booli.se real estate for Claude: search listings, sold prices, areas & market stats

URL to Clean Markdown for LLMs & RAG io.github.eltociear/url-to-markdown-for-llms

Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.

C4C: Mortgage Industry Regulations com.claudeforcompliance/mortgage-regs

Verbatim U.S. mortgage regulatory text with citations and effective dates. Read-only, no sign-in.

saymetry com.saymetry/saymetry

Measure what ChatGPT, Claude, Gemini and 4 more AI engines say about any business. No auth.

AIsa AI Visibility one.aisa/seo-ai-visibility

How a brand shows up in ChatGPT, Claude, Gemini and Perplexity answers.

ViewMax MCP net.viewmaxstudio/viewmax

Generate AI video from any MCP client. Pick the model, see the per-second price before you spend.

Project context for Cursor/Claude via stdio MCP. Key: www.neither.online/start

GenMagic io.github.yumaheymans/genmagic

Generate images, video, speech, music and text with 450+ AI models, one API key and one balance.

Price a Claude, GPT, Gemini or Grok call before you send it. Runs locally.

Manage Marzban panels through the Model Context Protocol.

gpt-4o-ksdwzw com.jojapi/gpt-4o-ksdwzw

GPT-4o: GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both.

SandBase io.github.sandbaseai/cli

Connect MCP clients to 2,000+ AI models without managing provider API keys.

kr-apt-trades io.github.HyosikPark/kr-apt-trades

Official Korean apartment sale prices (MOLIT). Clean JSON, data global models cannot know — paid pe…

Sigistry Plugin & Skill Catalog com.sigistry/plugin-catalog

Search verified Claude Code plugins and skills; fetch portable SKILL.md sources. Read-only.

COTRUGLI Agent Recruitment tech.cotrugli/agent-recruitment

Public read-only discovery of agent, model, training, task, and verification opportunities.

whatbreaks-mot io.github.physics-star-cat/whatbreaks-mot

Real UK MOT failure data by car model and mileage, aggregated from official DfT test results.

MCPFax Agent Continuity com.mcpscores/agent-continuity

Resume the work, not the conversation. A checkpoint by one model is resumable by another.

Token Counter com.apished/token-counter

Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.

ComputeSage StackBench com.computesage/stackbench

GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.

VAAS-X Cognitive Memory io.github.VAAS-X/vaasxmcp

Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.