pickfit

BrowseMCP servers

Buddy

Local-first MCP virtual pet that persists across sessions and reacts to coding work.

Tested on LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 17 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • npm:proxy-addr 2.0.7 proxy-addr vulnerable to IP spoofing via IPv4-mapped IPv6 trust subnet (GHSA-jqcg-44mw-7w3h, critical, fixed in 2.0.8)
  • npm:@modelcontextprotocol/sdk 1.29.0 MCP TypeScript SDK: Experimental tasks were not tied to the session that created them (GHSA-22jm-h49p-29qw, high, fixed in 1.32.0)
See 8 more

7 more findings not listed here.

Linux x86_64

You need first

  • Runtimes: node 18+
  • System packages: git
  1. Download installer script for inspection

    curl -fsSL https://raw.githubusercontent.com/fiorastudio/buddy/master/install.sh -o /tmp/buddy-install.sh
  2. Install Buddy via script without onboarding

    bash /tmp/buddy-install.sh --no-onboard
Where the README and reality differ
  • README: Requires node 18+
    What worked: Node 20+ is required (better-sqlite3 dropped 18/19 support)
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

curl -fsSL https://raw.githubusercontent.com/fiorastudio/buddy/master/install.sh -o /tmp/buddy-install.sh
bash /tmp/buddy-install.sh --no-onboard
node /home/sbx/.buddy/server/dist/cli/buddy.js --help

Check that it works

node "$HOME"/.buddy/server/dist/cli/buddy.js --help

The output should contain “Usage: buddy”.

Add it to your agent

claude mcp add buddy -- node $HOME/.buddy/server/dist/server/index.js
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "buddy": {
      "command": "sh",
      "args": [
        "-c",
        "exec node \"$HOME/.buddy/server/dist/server/index.js\""
      ]
    }
  }
}

Connect Buddy to your MCP client, then ask the assistant to call buddy_hatch with a name to create your pet.

What it does

  • Get code review feedback with personality
    How to use it
    1. Hatch your pet with buddy_hatch, giving it a name.
    2. Call buddy_observe with a short summary of the code change you made.
    3. Read the pet's reaction and feedback in the reply.
    Tested
  • Have your companion react to finished work
    How to use it
    1. Hatch your pet with buddy_hatch if you have not already.
    2. Call buddy_observe with a summary of the work you just finished.
    Tested
  • Save memories and keep your pet across sessions
    How to use it
    1. Hatch your pet with buddy_hatch, giving it a name.
    2. Call buddy_remember with the content you want it to remember.
    Tested
  • Gain XP and level up as you code
    How to use it
    1. Hatch your pet with buddy_hatch.
    2. Call buddy_status to see your pet's current XP and level.
    Tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 4 of 4 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.0.6

An MCP client handshake over stdio listed 13 tools, and a call to buddy_observe returned a result.

Differences the test machine hit

  • README: curl -fsSL .../install.sh | bash
    In the test: run installer with --no-onboard and launch server via node /home/sbx/.buddy/server/dist/server/index.js; /usr/local/bin symlinks fail without root

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.