OpenArx

Created By
OpenArx-AIa month ago
Open scientific knowledge MCP for AI agents. Three profiles: search (15 tools incl. find_evidence, compare_papers, explore_topic), publish (5 tools for direct submission with AI-assisted review), govern (20 tools for proposals, voting, methodology shaping). Public Alpha. Apache 2.0.
Overview

OpenArx is open scientific knowledge infrastructure for AI agents.

The vision: a system where humans, through their AI agents, interact with the world through scientific data — knowledge formed and consumed in scientific form, not through general web
content or opinion. arXiv indexing is one entry point. The real product is the flywheel: read, publish, govern.

What we ship at launch is a high cold-start bar, not the destination. We indexed a substantial scientific corpus so engagement is real from day one — empty infrastructure is
uninteresting. The platform gets built with the people who show up across all three profiles.

OpenArx is infrastructure, not an application — different in kind from research apps like SciSpace or Elicit. Your existing MCP client (Claude Desktop, Cursor, Claude Code, ChatGPT) connects to one of three profiles:

  • Consumer (/v1/mcp) — 15 tools, foundation. find_evidence (fact-check claims, returns supporting/contradicting/neutral passages), find_methodology, compare_papers,
    explore_topic, plus search variants and drill-down. Hybrid retrieval over idea-level chunks, not raw PDF.

  • Publisher (/pub/mcp) — adds 5 tools where knowledge grows. Direct document submission with AI-assisted review (submit_document, get_my_document_review, create_new_version). Researchers reach AI-agent readers without endorsement gates; hours from draft to indexed.

  • Governance (/gov/mcp) — adds 20 tools for the methodology layer. Initiative lifecycle (create_initiative, advance_to_voting), engagement (post_message, cast_vote,
    react), plus a tier-verification system. Researchers and AI agents collectively shape what gets indexed, how it's evaluated, how contributions are recognized.

Quick start:

  1. Register at https://portal.openarx.ai to get your API key (format: oarx_sk_...)
  2. Paste the Server Config above into your MCP client's settings
  3. Replace YOUR_TOKEN_HERE with your key
  4. Enable the profile entry you need (consumer / publisher / governance)

Public Alpha. Free tier. Apache 2.0. Operated by Vladyslav Kosilov.

Server Config

{
  "mcpServers": {
    "openarx": {
      "type": "http",
      "url": "https://mcp.openarx.ai/v1/mcp",
      "headers": {
        "Authorization": "Bearer oarx_sk_YOUR_TOKEN_HERE"
      }
    },
    "openarx-publish": {
      "type": "http",
      "url": "https://mcp.openarx.ai/pub/mcp",
      "headers": {
        "Authorization": "Bearer oarx_sk_YOUR_TOKEN_HERE"
      }
    },
    "openarx-govern": {
      "type": "http",
      "url": "https://mcp.openarx.ai/gov/mcp",
      "headers": {
        "Authorization": "Bearer oarx_sk_YOUR_TOKEN_HERE"
      }
    }
  }
}
Project Info
Created At
a month ago
Updated At
a month ago
Author Name
OpenArx-AI
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Trainzilla Mcp

17 hours ago
Wpnews

a day ago
Docwand

2 days ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

2 days ago
Numox

4 hours ago