Cerebrum

org.askcerebrumPublished by askcerebrum.orgOfficial publisherv1.0.0Updated Oct 24, 2026

Search the scientific literature and get a cited answer, plus the Trending in Science edition.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Cerebrum is a remote MCP server that lets an assistant search scientific literature for cited answers and fetch a daily science headline digest.

What you can do
Search the scientific literature with a research question and get a cited answer with a numbered source list, drawn from open scholarly databases and linked to papers you can open and check. Retrieve the current Today in Science edition with top headlines grouped by section and links to the original stories.
When to use it
Useful when an assistant needs evidence from papers rather than general knowledge, or when you want a quick, sectioned overview of current science news.
Requirements
A remote endpoint at askcerebrum.org over streamable HTTP; no packages, environment variables, headers or authentication are declared. Network access is needed.
Before you install
Answers and headlines come from third-party sources and AI-generated summaries, so citations should be opened and checked before relying on them. The README mentions server-side API keys for deployment, but the MCP endpoint itself declares no credentials.

Installation

In SourceWeft

  1. Open Cerebrum 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/org.askcerebrum%2Fcerebrum/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": {
    "cerebrum": {
      "type": "http",
      "url": "https://askcerebrum.org/mcp"
    }
  }
}

README

Cerebrum

A scientific literature search engine at askcerebrum.org.

Ask a question. Cerebrum searches 14 open scholarly databases in parallel, then writes an answer whose citations link to papers you can open and check.

The count is not typed here — it is derived from SCHOLARLY_SOURCES in functions/lib/product.js, and npm run check fails the build if any copy in the repository disagrees with it.

Stack

  • Frontend: React + Vite, deployed as static site on Cloudflare Pages
  • Backend: Cloudflare Pages Functions (functions/api/search.js)
  • AI: OpenRouter free models (Gemini Flash, DeepSeek, Llama, Qwen, Mistral) + Pollinations legs + Cloudflare Workers AI fallback
  • Databases: see SCHOLARLY_SOURCES in functions/lib/product.js for the authoritative list
  • Animation: GSAP for choreography, OGL for the WebGL background. Both bundled; nothing is loaded from a CDN.

Deploy

bash
npm installnpx wrangler loginnpm run deploy

Then add secrets (once):

bash
npx wrangler pages secret put OPENROUTER_KEYnpx wrangler pages secret put OPENALEX_KEY          # optionalnpx wrangler pages secret put NCBI_API_KEY          # optional

Local development

bash
npm installcp dev.vars.example .dev.vars    # fill in your OPENROUTER_KEYnpm run dev

Cost

Everything runs on free tiers. Cloudflare Pages (100k requests/day), OpenRouter free models, and free scholarly APIs.

Built by

Vaticay

Source: README.md at commit 018edd1

Tools

2

search_literature

Search the literature

Search the scientific literature for a research question and return a cited answer with a numbered source list. Use this when you need evidence from papers rather than general knowledge.

Parametersqueryrequired

Version history

1
  1. v1.0.0LatestOct 14, 2026

Score

90% 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
  • License10 pts

    Declare a license in the repository or the registry entry.