MCP Server Directory

Garmin & Strava for Claude and ChatGPT training.stats/garmin

Read-only Garmin and Strava data for your AI: activities, sleep, HRV, readiness, training load.

Give LLM agents webcam access: capture photos and record short videos over MCP.

Store API com.store-api/store-api

GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.

Kourier sh.kourier/info

Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.

Mode VC Chart: Open Weights vs. Proprietary AI: The Gap Stays at 42 Points com.modevc/chart-open-weights-vs-proprietary-arena-gap

Open weights briefly beat every proprietary model in early 2025 (deepseek-r1); today the best.

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.

Mode VC Chart: Gemini Leaderboard Ranking: Google's Days at #1 com.modevc/chart-gemini-leaderboard-ranking-days-at-number-one

Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.

Mode VC Chart: Arena Rating Gap: Google Leads; Anthropic Trails by 22 Pts com.modevc/chart-arena-rating-gap-google-anthropic-openai

Google leads the Arena again; Anthropic trails by 22 points and OpenAI by 62. Query full.

Mode VC Chart: AI Model Launch Strategy: What Labs Ship on Day One com.modevc/chart-ai-model-launch-strategy

Of 13 model launches from 23 Sept 2026 to 3 Oct 2026, 9 opened an API on day one, 7 of them.

Runs non-urgent LLM tasks at the cleanest grid hour before a deadline, via Batch APIs when allowed.

Nutrition by Pack4Back com.pack4back/nutrition

Log meals, water, and weight to Garmin Connect from Claude or ChatGPT.

Oh My Share io.github.shisongsong/oh-my-share

Publish HTML/code from your agent to openanthropic.com and get a shareable link.

Keeps AI coding agents' plan and design markdown managed and versioned, for Claude Code and Codex.

CompanyGraph io.companygraph/mental-model

CompanyGraph: Written once, read by both

Minutes of AI com.minutesofai/mcp

Read-only AI news with sources, Model Tracker prices, releases and retirement dates.

Colle com.trycolle/colle

Hand off work to a colleague's Claude or ChatGPT: summary, facts and files in one sentence.

Krankenkasse Copilot app.vercel.krankenkasse-copilot/krankenkasse-copilot

Swiss health insurance 2027: rank every insurer, model and deductible with official BAG data.

Mode VC Chart: AI Chatbot Adoption by Age: ChatGPT Hits 61% in Youth com.modevc/chart-ai-chatbot-adoption-by-age-demographics

61% of Americans aged 18–29 use ChatGPT; Claude reaches 6% of all adults. Query full empirical.

Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data

Stack Facts us.srv.g5joilnmeep4ntz3nwezxt5dmu/stackfacts

Signed EOL dates, exploited CVEs and LLM prices; pay per call in USDC, no account, no daily cap.

Vibe Marketolog — landing A/B tests and Yandex Direct ru.vibemarketolog/vibemarketolog

Landing A/B tests, Yandex Wordstat, Metrika, Direct and 170+ AI models in ChatGPT, Claude, Cursor

TuringCorp net.turingcorp.mcp/decider

A decision model for the calls that don't have a right answer. The better option, with a reason.

Protologue com.protologue/protologue

Sourced, citable definitions of prompting and LLM techniques, with relations and primary sources.

Crivum org.crivum/crivum

Score academic and professional writing against published criteria with three reference models.