pickfit

BrowseMCP servers

prod-code

Remote code intelligence gateway that gives AI agents semantic search and safe refactoring with builds on LAN nodes.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • Runtimes: Rust 1.95.0 or newer
  1. download install script

    curl -fsSL https://prod.codes/install.sh -o /tmp/install.sh && wc -c /tmp/install.sh && head -n 200 /tmp/install.sh
  2. install prod-code v0.3.47 via script

    VERSION=v0.3.47 sh /tmp/install.sh
Where the README and reality differ
  • README: curl -fsSL https://prod.codes/install.sh | sh installs latest
    What worked: script queries GitHub API for latest tag, hits rate limit and falls back to v0.3.19 which has no binary (404); need VERSION=v0.3.47 sh /tmp/install.sh to get a release with binaries

Add it to your agent

claude mcp add prod-code -- prod-code mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "prod-code": {
      "command": "prod-code",
      "args": [
        "mcp"
      ]
    }
  }
}

Add prod-code as an MCP server in your AI agent's client, then ask the agent to use its code tools such as code_definition or code_test.

Linux x86_64

You need first

  • Runtimes: Rust 1.95.0 or newer
  1. download install.sh from https://prod.codes/install.sh

    curl -fsSL https://prod.codes/install.sh -o /tmp/install.sh && ls -lh /tmp/install.sh && head -n 200 /tmp/install.sh
  2. run install.sh to install prod-code binary to ~/.local/bin

    sh /tmp/install.sh

Check that it works

prod-code --version

The output should contain “prod-code 0.3.45”.

First thing to try

prod-code cluster

Add it to your agent

claude mcp add prod-code -- prod-code mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "prod-code": {
      "command": "prod-code",
      "args": [
        "mcp"
      ]
    }
  }
}

Add prod-code as an MCP server in your AI agent's client, then ask the agent to use its code tools such as code_definition or code_test.

What it does

  • Search and navigate remote code by meaning
    Not shown working
  • Refactor code safely
    Not tested
  • Run builds and tests on remote machines
    Not tested

How far pickfit got

macOS arm64

  1. Installs
  2. Connects
  3. 0 of 3 features work
  4. Works offline

Linux x86_64

  1. Installs
  2. Connects
  3. 0 of 3 features work
  4. Works offline

Good for

  • find code by natural language query
  • find symbol definition and references across workspace
  • run compile check, lint, and tests on remote node

How pickfit tested it

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

macOS arm64

An MCP client connects and lists its tools

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 0.3.47

An MCP client handshake over stdio listed 70 tools.

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 0.3.45

An MCP client handshake over stdio listed 70 tools, and a call to code_grep returned a result.

Differences the test machine hit

  • README: install .deb v0.3.29 and cargo install examples reference 0.3.29
    In the test: install.sh fetched latest v0.3.45; binary reports 0.3.45

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.