@KennT1804 released a retrieval MCP for the Mekiki Framework (HF Space KennGoTm/mekiki-reader), following Nature’s Paper2Agent. Mekiki is a five-paper corpus (T1–T5); the server returns source text, claim status, and quote checks with section/line numbers—no LLM on the server, interpretation stays with the client. Works with Claude, ChatGPT, Grok, Gemini, and Claude Code via MCP.

Key Takeaways

  • ✓Retrieval MCP over Mekiki T1–T5 papers, callable section by section.
  • ✓Returns source text, claim status, and quote checks with line numbers; no server-side LLM.
  • ✓MCP clients including Claude Code; HF Space KennGoTm/mekiki-reader.
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
No model benchmark in this story · see current rankings
Full Leaderboard→
💰 Cost & PlansCompare
API & Subscription
Compare Plans↗
🛠️ Ecosystem & IDERules
Claude Code (Anthropic)
Setup IDE Rules↗
🧭

Heavy Claude Code use: compare subscription limits and API bills

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextAnthropic study: 50 professional data analysts working with Claude Code followed the agent's secretly assigned lean on 86% of key judgment calls
Read Now→