1774 Model Context Protocol servers — searchable, rated, ready to install.
Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.
The Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.
Local chronological memory banks you control; Claude recalls them via MCP.
Research Hadith, authenticity, grading, Takhrij and Sharh [commentaries] in Claude Desktop for free.
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.
Analyze LLM API costs: token waste detection, caching savings estimates, model comparison
Closed-source remote MCP: model benchmarks, costs, HN signals, tech registry.
Discover Frontier inference capabilities and read sanitized usage through read-only tools.
Connect Claude to a self-hosted Total CMS site: search content, read docs, manage with an API key.
Rewrites Claude-English into plain English, preserving meaning, code and structure.
Agent-native parametric 3D CAD: model machines, validate them and emit shop drawings
Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.
Local-first RAG MCP server: hybrid search over a folder of your own documents
Generate and manage ComfyUI media through the Model Context Protocol.
AIO.GEO: audit, dry-run fixes, rescore, doctor. Remote + stdio. Not LLM rankings.
Causal root-cause analysis MCP server -- 56 tools across graphs, RCA models, PyRCA.
LLM pricing where every rate carries its source and the date it was last confirmed.
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Turn HTML, Claude Design bundles or mobile-learning exports into SCORM 2004/1.2 packages.
Low-poly 3D models and kits for three.js and game engines: search, match, remix, preview.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
Shared memory for a team in Claude Code: what one person records, everyone has.
POST /mcp