pickfit

BrowseMCP servers

code-cortex-mcp

Local MCP server that indexes codebases into a queryable knowledge graph for AI coding agents.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • System packages: CMake, C++23 compiler, zlib
  1. download install.sh from GitHub

    curl -fsSL https://raw.githubusercontent.com/tigercosmos/code-cortex-mcp/main/install.sh -o /tmp/install.sh && wc -l /tmp/install.sh && head -n 100 /tmp/install.sh
  2. run install.sh --skip-config to install binary to ~/.local/bin

    bash /tmp/install.sh --skip-config

Check that it works

code-cortex-mcp --version && which code-cortex-mcp && ls -l ~/.local/bin/code-cortex-mcp

The output should contain “code-cortex-mcp 0.23.0”.

Add it to your agent

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

Add code-cortex-mcp as an MCP server in your AI coding client, then ask the agent to call index_repository on your project folder.

Linux x86_64

You need first

  • System packages: CMake, C++23 compiler, zlib
  1. download install.sh

    curl -fsSL https://raw.githubusercontent.com/tigercosmos/code-cortex-mcp/main/install.sh -o /tmp/install.sh
  2. run install.sh --skip-config to install portable binary

    bash /tmp/install.sh --skip-config

Check that it works

code-cortex-mcp --version

The output should contain “code-cortex-mcp 0.23.0”.

Add it to your agent

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

Add code-cortex-mcp as an MCP server in your AI coding client, then ask the agent to call index_repository on your project folder.

What it does

  • Index a codebase into a queryable knowledge graph
    How to use it
    1. Connect code-cortex-mcp to your MCP client.
    2. Call the index_repository tool with repo_path set to <your project folder>.
    Tested
  • Search code with graph-aware grep
    How to use it
    1. Index your project first with index_repository.
    2. Call the search_code tool with pattern set to <your text> and project set to <project name>.
    Tested
  • Trace call paths and data flow
    Not shown working
  • Inspect a symbol's definition and callers
    Not shown working

How far pickfit got

macOS arm64

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

Linux x86_64

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

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

Good for

  • inspect a symbol definition with callers and related tests
  • trace call chains between functions
  • search code augmented by the graph

An alternative to codebase-memory-mcp.

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 0.23.0

An MCP client handshake over stdio listed 15 tools, and a call to index_repository returned a result.

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 0.23.0

An MCP client handshake over stdio listed 15 tools, and a call to index_repository returned a result.

Differences the test machine hit

  • README: curl -fsSL ... | bash installs and configures agents
    In the test: used --skip-config to avoid modifying Claude Code/Codex etc. configs in the box; still installs binary correctly
  • README: project argument optional, inferred from working directory
    In the test: MCP tool calls outside indexed directory require explicit "project" (e.g., tmp-testproj) else error

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.