LABSCO SUMMARY

Curation is the whole argument.

The pitch is not that it searches more but that it searches better material — newsletters written by developers about things they built, rather than SEO pages restating documentation. Returning URLs instead of full text is deliberate and works in an agent's favour: the model triages descriptions cheaply and only fetches what it will actually use. Take the remote endpoint unless you have a reason not to; the local route's known Claude and uvx issues are documented precisely because they bite.

What it is

A newsletter-backed research server. Rather than searching the whole web, it searches a curated body of developer-written newsletters, articles and blog posts, and you can plug in your own favourite newsletter to widen the base. Results come back as a short description plus a URL.

What you get

Topic research across high-quality, developer-curated content rather than generic search results
A results shape built for agents: short description plus URL, so the model can then fetch the full article for the ones worth reading
Your own newsletters added to the knowledge base to widen what is searchable
Three ways to run it — a remote HTTP endpoint, a local stdio process, or a Docker container

Requirements

The recommended path needs nothing installed: point the client at https://devbrain.svenai.com/mcp as an http server. Locally it runs through uvx as uvx --python ">=3.10" --from devbrain devbrain-stdio-server, so Python 3.10+ is required — the README warns that VS Code ships 3.9, which is why the version constraint is on the command. Claude Desktop needs --force-reinstall in the args to pick up the current version, and the README documents the known uv and uvx path problem with symlinks into /usr/local/bin as the fix. Docker is svenai/mcp-devbrain-stdio:latest. The package is devbrain (version 1.1.9). MIT licensed.

Setup effort

Add the hosted endpoint — paste it into your client

See installation options

USE CASES

01

Finding a real implementation before writing your own

Research the feature you are about to build and pull articles from people who already shipped it.

02

Getting past generic search results

Search curated developer writing rather than pages that restate the documentation you already read.

03

Turning research into implementation

Have the agent fetch the full text of the selected articles and build from them as a reference.

04

Including a newsletter you rely on

Plug your own source into the knowledge base so your reading list becomes searchable.

INSTALLATION

Connect your client

Server setup

ENDPOINT URL

https://devbrain.svenai.com/mcp

Add this hosted endpoint to your MCP client.

MCP Clients

Any MCP client — remote

ANY MCP CLIENT — REMOTE · JSON

{
  "mcpServers": {
    "devbrain": {
      "type": "http",
      "url": "https://devbrain.svenai.com/mcp"
    }
  }
}

Claude Desktop, Cline

JSON

{
  "mcpServers": {
    "devbrain": {
      "command": "uvx",
      "args": [
        "--python",
        ">=3.10",
        "--force-reinstall",
        "--from",
        "devbrain",
        "devbrain-stdio-server"
      ]
    }
  }
}

Claude Desktop — Docker

CLAUDE DESKTOP — DOCKER · JSON

{
  "mcpServers": {
    "devbrain": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "svenai/mcp-devbrain-stdio:latest"
      ]
    }
  }
}

DevBrain