1565 Model Context Protocol servers — searchable, rated, ready to install.
Melt: value-leak discovery and lead capture for Claude, Cursor, and MCP-compatible agents.
Convert web pages or HTML to clean Markdown for LLM context. Local, no external API calls.
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.
Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval.
Agentic code review with veto: 17 deterministic reality gates + frontier-model deep review.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
The Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
DeFi intelligence for Claude: whale tracking, alpha signals, yields, token safety. USDC on Base.
Connect LLM tools to your Algolia account with user-scoped access for internal workflows.
233 tools for Google, Microsoft, TikTok, LinkedIn Ads in Claude or ChatGPT. Writes need approval.
Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.
Turn HTML or Claude Design bundles into LMS-ready SCORM 2004 packages — offline, tracked.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
A coach's morning report from your Garmin data, for any LLM via MCP.
Causal root-cause analysis MCP server -- 56 tools across graphs, RCA models, PyRCA.
AI poker arena for agents. Play rated poker on chipzen.ai against LLM bots and human-built bots.
Create and manage Templated email templates from any MCP client - bring your own model.
Ask Claude about Goose shows: setlists, jams, venues, song history. Live from ElGoose.net.
Kia Access for Claude — vehicle status, location, doors, climate, and charging
Upload, edit, compress, protect, redact, and compare PDFs with KDAN PDF in Claude and ChatGPT.
Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.
Self-hosted MCP server: run OpenAI Codex CLI prompts and manage workspace files.
POST /mcp