MCP Server Directory

Read-only stdio MCP server for a versioned convention card in Claude Code.

Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients.

ASR Memory (에사 AI) — Shared memory for AI tools com.asrmemory/asr

Shared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.

ENSEMBLE markets.ensemble/ensemble

Cloud platform for asset research and investment allocation models, saving code, runs and outputs.

Hands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source

JSON to TOON io.github.karta9821/json2toon

Convert JSON to TOON (about 43% fewer LLM tokens) and TOON back to JSON. Free, no auth.

Ephemeris Time-Series Forecasting industries.cascade/ephemeris

Probabilistic time-series forecasts from zero-shot foundation models: routed, single or ensembled.

Records the prompt, model and files an agent declared for a line. It does not prove who typed it.

apimodels io.github.stimQQ/apimodels-mcp

Chat, image, video, speech, music and media models with one account — local (npx) or hosted.

Duffer Golf net.duffergolf/duffer-golf

Read-only Duffer Golf facts: models and prices, room fit, FAQ, dealers and contact.

Mode VC Chart: Ollama Downloads: Is Local LLM Adoption Keeping Up? com.modevc/chart-ollama-downloads-local-llm-adoption

On npm, Ollama's client fell from 27 to 6.6 downloads per 1,000 cloud lab SDK downloads in 46.

Chatty: WhatsApp Business com.letschatty/whatsapp

Your WhatsApp Business inbox in Claude or ChatGPT: who's waiting, follow-ups and replies.

Claude distils its past sessions into linked Markdown notes on disk and searches them later.

Amazon Seller Central and Ads in Claude or ChatGPT. Connect at agentxray.ai/connect.

MCP server for WoW addons: Lua API, UI source, CVars, art, linting, plus model export to glTF/OBJ.

Which parts of an ML need Hugging Face already covers. Every model and dataset checked live.

Private audio and video transcription with Whisper on your own computer, on the GPU or CPU.

Cheapest LLM API io.github.tehtelabs/cheapestllmapi

Compare LLM API prices, search models and providers, and access reviewed benchmark results.

InferIndex io.github.InferIndex/inferindex

LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates.

FIDE Laws of Chess io.arxo/fide-chess

FIDE Laws of Chess (2023) as an executable model: arbiter cases, answers with rules and judgments

Background sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP, with a spend cap.

Typed noul / choice / score judgments from a local Laya model, with token-budget preflight.

DexL Agents io.github.dexl-io/agents

Pay-per-call AI gateway: models, speech, web search, on-chain reads and NLP tools, via x402.

Mode VC Chart: Best LLM for Coding: The Arena Coding Leaderboard com.modevc/chart-best-llm-for-coding

claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.