pickfit

BrowseMCP servers

gen-system

Parser-based code review that reports break risks, effects, and coverage.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • A GPU is optional
  1. install gen-understand via npm install -g gen-understand

    npm install -g gen-understand
Where the README and reality differ
  • README: MCP tool review_diff for code-change review
    What worked: tool not present in npm release 0.2.0 (8 tools listed); README notes it arrives in next release and currently requires building understand-mcp from source

Check that it works

gen-understand --version

The output should contain “understand-mcp 0.2.0”.

Add it to your agent

claude mcp add gen-system -- gen-understand --root '<root>'
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "gen-system": {
      "command": "gen-understand",
      "args": [
        "--root",
        "<root>"
      ]
    }
  }
}

Replace <root> with your own path.

Add gen-understand --root <your repo> as an MCP server in your MCP client, then call its tools such as effects or call_graph.

Linux x86_64

You need first

  • A GPU is optional
  1. install gen-understand via npm

    npm install -g gen-understand

Add it to your agent

claude mcp add gen-system -- gen-understand --root '<root>'
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "gen-system": {
      "command": "gen-understand",
      "args": [
        "--root",
        "<root>"
      ]
    }
  }
}

Replace <root> with your own path.

Add gen-understand --root <your repo> as an MCP server in your MCP client, then call its tools such as effects or call_graph.

What it does

  • See what code touches, such as files or network
    How to use it
    1. Add gen-understand --root <your repo> as an MCP server in your client.
    2. Call the effects tool to list routines that touch files, network or databases.
    Tested
  • View call graphs and control flow
    How to use it
    1. Add gen-understand --root <your repo> as an MCP server in your client.
    2. Call call_graph with a symbol such as <file>#func:<name> to see its callers and callees.
    3. Call control_flow with a symbol such as <file>#func:<name> to see its branches.
    Tested
  • Review code changes using parser facts
    Not shown working

How far pickfit got

macOS arm64

  1. Installs
  2. Connects
  3. 2 of 3 features work
  4. Needs the network

Linux x86_64

  1. Installs
  2. Connects
  3. 2 of 3 features work
  4. Needs the network

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

Good for

  • review code changes for breaking callers in CI
  • find callers or callees of a symbol
  • list routines that touch database, files or network

How pickfit tested it

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

macOS arm64

An MCP client called one of its tools

  • Replayed from scratch
  • Needed the network
  • Checked on 1 Nov 2026
  • Version 0.2.0

An MCP client handshake over stdio listed 8 tools, and a call to effects returned a result.

Differences the test machine hit

  • README: npx -y gen-understand --root <repo> with tool review_diff
    In the test: npm package gen-understand 0.2.0 wraps understand-mcp binary cached at ~/.cache/gen-understand/0.2.0/understand-mcp-darwin-arm64; launch as gen-understand --root <repo> and binary downloads on first run

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Needed the network
  • Checked on 1 Nov 2026
  • Version 0.2.0

An MCP client handshake over stdio listed 8 tools, and a call to effects returned a result.

Differences the test machine hit

  • README: MCP tool review_diff available via npx gen-understand
    In the test: version 0.2.0 from npm exposes only 8 tools; review_diff not yet included — README notes it arrives with next release and requires building understand-mcp from source until then

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.