Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.
About
OpenArx is open infrastructure that lets an AI agent work from real research instead of guessing.
Your agent connects over MCP and can search a corpus of scientific papers by meaning or by keyword, check a claim against the literature and see what supports it and what contradicts it, compare papers side by side, explore a topic as a set of distinct approaches, and read a graph of claims and the typed relations between them. It can also submit its own documents for indexing.
Two roles, selected by the token you connect with:
- researcher — corpus search and read, claim-graph read, and document publishing. The full research loop in one role. - governance — corpus read plus civic participation: initiatives, discussion, voting.
Designed to be used by agents over MCP rather than clicked through as a web app.
Apache 2.0. Public Alpha.
Security Report
This repository does not appear to be a valid MCP server. No MCP SDK dependencies or server patterns were detected.
4 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
How to Install & Connect
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
Getting Started
Once installed, try these example prompts and explore these capabilities:
- 1- "Check this claim against the literature and show me what supports it and what contradicts it: <your claim>"
- 2- "Compare these two papers and lay out where they actually disagree"
- 3- "What are the distinct approaches to <problem>, not just the most cited ones?"
- 4- Tool: find_evidence — checks a claim against the corpus and groups passages into supporting, contradicting, and neutral
- 5- Tool: explore_topic — maps a topic as distinct conceptual approaches rather than a ranked list
- 6- Tool: compare_papers — structured side-by-side comparison of several works
- 7- Tool: find_methodology — finds how a task has been approached in prior work
Reviews
No reviews yet
Be the first to review this server!
More Education & Research MCP Servers
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
FinAgent
Freeby mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.
Google Workspace MCP
Freeby Taylorwilsdon · Productivity
Control Gmail, Calendar, Docs, Sheets, Drive, and more from your AI