pickfit

BrowseMCP servers

aptu-coder

MCP code-intelligence server that gives agents symbol tables and call graphs via tree-sitter.

Tested on macOS and Linux

Use it

macOS arm64

  1. brew install clouatre-labs/tap/aptu-coder

    brew install clouatre-labs/tap/aptu-coder

Check that it works

aptu-coder --version

The output should contain “aptu-coder 0.41.1”.

Add it to your agent

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

Add aptu-coder as an MCP server command in your MCP client, then ask the agent to use its tools such as analyze_directory.

Linux x86_64

  1. Install binary to ~/.local/bin

    mkdir -p ~/.local/bin && curl -fsSL -o /tmp/aptu2.tar.gz https://github.com/clouatre-labs/aptu-coder/releases/download/v0.41.1/aptu-coder-0.41.1-x86_64-unknown-linux-musl.tar.gz && tar -xzf /tmp/aptu2.tar.gz -C /tmp && cp /tmp/aptu-coder ~/.local/bin/aptu-coder && chmod +x ~/.local/bin/aptu-coder

Check that it works

cp /tmp/aptu-coder ~/.local/bin/aptu-coder && chmod +x ~/.local/bin/aptu-coder && aptu-coder --version

The output should contain “aptu-coder 0.41.1”.

Add it to your agent

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

Add aptu-coder as an MCP server command in your MCP client, then ask the agent to use its tools such as analyze_directory.

What it does

  • Map a directory tree with symbol counts
    How to use it
    1. In your MCP client, call the analyze_directory tool.
    2. Set path to <your project folder>.
    Tested
  • List the functions, classes and imports in a file
    How to use it
    1. In your MCP client, call the analyze_file tool.
    2. Set path to <your source file>.
    Tested
  • Trace the call graph for a named symbol
    How to use it
    1. In your MCP client, call the analyze_symbol tool.
    2. Set path to <your project folder> and symbol to <symbol name>.
    Tested

How far pickfit got

macOS arm64

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

Linux x86_64

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

Good for

  • map directory structure of a codebase
  • extract symbols from source files
  • trace call graphs for a named symbol

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
  • Works offline
  • Checked on 1 Nov 2026
  • Version 0.41.1

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

Differences the test machine hit

  • README: README shows tools take a `path` without mentioning sandboxing
    In the test: path must be inside the server's working directory; passing /tmp/mcp_test_proj returns 'path is outside the working directory' and suggests providing a path within the current working directory

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.41.1

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

Differences the test machine hit

  • README: cargo binstall aptu-coder / cargo install aptu-coder
    In the test: downloaded x86_64-unknown-linux-musl tarball from GitHub releases v0.41.1 and copied aptu-coder to ~/.local/bin; both ranked cargo candidates need a Rust toolchain which the box does not have and must not install
  • README: tools take a path argument
    In the test: run probe from the analyzed directory (cd /tmp/sampleproj) and pass relative paths ('.', 'demo.py'); absolute paths outside cwd fail with 'path is outside the working directory'

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.