3307 Model Context Protocol servers — searchable, rated, ready to install.
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
Overte (open-source Vircadia-lineage metaverse) Model Context Protocol server for domain administ...
A live, curated feed of new AI agent capabilities across MCP, SDKs, models, and APIs.
Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Booli.se real estate for Claude: search listings, sold prices, areas & market stats
Official Korean apartment sale prices (MOLIT). Clean JSON, data global models cannot know — paid pe…
A fast, configurable filesystem server for the Model Context Protocol (MCP), written in Rust.
Build, edit, solve and analyse Convexity energy-system models from any MCP client; drives the app.
Public read-only discovery of agent, model, training, task, and verification opportunities.
Ship models, build logs, tutorials, galleries, content search, and rope diameter calculator.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Single-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.
Multiple Google accounts (Gmail, Calendar, Drive, Contacts, Tasks) in one Claude connector.
Generate reproducible image, video, and audio assets with leading models and your own provider keys.
Ask Claude or ChatGPT about your own credit cards: best card to use, utilization, missed rewards.
Compare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.
Yappy macOS docs (yappy.biz): setup, permissions, LLM backends, troubleshooting.
Bambara AI over MCP: text-to-speech, transcription and translation (Bamanankan + more).
Checks a claim's numbers, names and file names against your indexed notes. Local; no model.
Monte Carlo NFL, MLB, NHL, NBA and soccer odds, plus model-vs-market edge from live prices
Compose and render video from one JSON template. Deterministic, runs locally, no generative model.
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
POST /mcp