3073 Model Context Protocol servers — searchable, rated, ready to install.
Self-hosted architecture model that agents read layer by layer, search, build and correct.
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
UK car repair and servicing cost ranges per car model, in GBP, from PriceMyRepair.
LLM releases: new models, availability, context. Register in-session — free testnet funds.
Deploy websites; manage apps, Kafka, VMs, backups, S3 buckets and VPC names; browse AI models.
Cut LLM agent token use in Claude Code, Cursor, Codex, Gemini CLI. Local, no API key. gAI Ventures.
Design domain models and generate deterministic multi-stack code, driven by your coding agent.
Give it a URL, get structured rows. A model writes the parser once; replays are free.
Truck & trailer load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in chat.
Speech-to-text transcription for AI agents.
Ping-only MCP origin for claude.ai, Desktop, Cursor, and Grok Connectors.
Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction
Claude 나 Codex 에서 벨로그(velog.io) 글을 읽고 쓰고 백업한다. 다이어그램과 시퀀스도 그린다. 공개 발행은 사람이 켤 때만 열린다.
Strips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.
Multi-agent coordination outside your LLM context: dedupe parallel work, per-agent budgets, handoff
Schedule webhook calls, pay per run in USDC on Base via x402. Ten tools, built for small models.
Shared memory and actions for Claude, Kiro, OpenAI, Cursor, and other MCP-compatible AI clients.
Single-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.
Generate AI images and videos from any compatible MCP client.
Multiple Google accounts (Gmail, Calendar, Drive, Contacts, Tasks) in one Claude connector.
Model Context Protocol server for live & historical sports stats and odds via ESPN.
63 tools an LLM can't do alone, in focused subsets: file edits, live data, real checksums.
Look up a vehicle by license plate against official sources (make/model, year, status, restrictions)
Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent.
POST /mcp