AxenomIA AX-SCI-001 — Scientific Novelty & Evidence

io.github.Perlita2013Published by GitHub account Perlita2013v1.0.1Updated Oct 27, 2026

Traceable scientific novelty and evidence assessment with source-linked results and a human gate.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Remote MCP server that lets an assistant gather source-linked scientific evidence for a research question and read the agent's scope and human-review rules.

What you can do
  • Read the versioned Agent Passport describing scope, evidence rules, evaluation status and limitations
  • Check the mandatory human-review boundary that applies to assessments
  • Research and synthesize traceable scientific evidence for a research question, returning provisional findings, verification depth, gaps and next evidence needs
When to use it
Useful when you want an assistant to assemble traceable, source-linked evidence around a research question and see where the evidence is thin, while keeping novelty, patentability and publication calls with a human.
Requirements
A remote streamable HTTP endpoint; no local package. An Authorization header carrying a Bearer API key is required for billable evidence-assessment runs; the Passport and human-gate tools are read-only and need no key.
Before you install
The evidence-assessment tool is billable and needs an API key sent in the Authorization header, so expect usage costs and keep the key private. Results are provisional and the server explicitly does not approve patentability, novelty, publication or research-priority decisions; those remain human-gated. Research questions are sent to a third-party service.

Installation

In SourceWeft

  1. Open AxenomIA AX-SCI-001 — Scientific Novelty & Evidence in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Perlita2013%2Fax-sci-001/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "axenomia-ax-sci-001-scientific-novelty-e": {
      "type": "http",
      "url": "https://axenomia.cl/mcp"
    }
  }
}

README

This repository has no README.

Tools

3

axenomia_agent_passport

AX-SCI-001 Agent Passport

Read the versioned AX-SCI-001 Agent Passport: scope, evidence rules, evaluation status, limitations and human-review requirements.

Takes no parameters.

axenomia_human_review_gate

AX-SCI-001 Human Review Gate

Return the mandatory human-review boundary for AX-SCI-001. This tool never approves patentability, novelty, publication or research-priority decisions.

Takes no parameters.

ax_sci_001_assess_evidence

Assess scientific novelty evidence

Research and synthesize traceable scientific evidence for a research question. Returns provisional evidence findings, verification depth, gaps and next evidence needs. Final novelty, patentability and publication judgments remain human-gated.

ParameterstopicreferencesmaxReferencesresearchQuestionrequiredproposedContribution

Version history

2
  1. v1.0.1LatestOct 1, 2026
  2. v1.0.0Sep 25, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.