pickfit

BrowseMCP servers

Code Index MCP

An MCP server that lets AI assistants index, search, and analyze code repositories.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.10, uv
  1. uv tool install code-index-mcp (puts code-index-mcp on PATH)

    uv tool install code-index-mcp

Add it to your agent

claude mcp add code-index-mcp -- code-index-mcp --project-path '<project-path>'
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "code-index-mcp": {
      "command": "code-index-mcp",
      "args": [
        "--project-path",
        "<project-path>"
      ]
    }
  }
}

Replace <project-path> with your own path.

Add code-index-mcp --project-path <your project> as an MCP server in your AI assistant, or run it over HTTP with `code-index-mcp --project-path <your project> --transport streamable-http --port <por

What it does

  • Search code with regex and fuzzy matching
    How to use it
    1. Connect your assistant to code-index-mcp --project-path <your project>.
    2. Call the search_code_advanced tool with a pattern such as <your regex> and regex set to true.
    Tested
  • Parse code symbols in 10 languages with tree-sitter
    How to use it
    1. Start code-index-mcp --project-path <your project> --transport streamable-http --port <port> and connect your assistant to http://127.0.0.1:<port>/mcp.
    2. Call the build_deep_index tool.
    3. Call get_symbol_body with a file_path and a symbol_name to see that symbol's code.
    Tested
  • Summarize a file's structure and complexity
    How to use it
    1. Start code-index-mcp --project-path <your project> --transport streamable-http --port <port> and connect your assistant to http://127.0.0.1:<port>/mcp.
    2. Call the build_deep_index tool.
    3. Call get_file_summary with the file_path of the file you want summarized.
    Tested
  • Refresh the index automatically when files change
    Not shown working

How far pickfit got

Linux x86_64

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

Good for

  • find all places in a codebase that use an old API
  • locate where a function is called
  • search for error handling code while debugging

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 15 Nov 2026

An MCP client handshake over stdio listed 14 tools, and a call to search_code_advanced returned a result.

Differences the test machine hit

  • README: Run build_deep_index, then get_file_summary uses the deep index (the README says indexes are persistently cached).
    In the test: When the server was started again over stdio in a separate process, it did not load the deep index built earlier: get_file_summary returned needs_deep_index (command 7) and get_symbol_body returned 'deep index not built' (command 8). To run several calls against one server, I started it with --tran…
  • README: Launch with uvx code-index-mcp
    In the test: uv tool install code-index-mcp, then launch code-index-mcp (with --project-path to skip calling set_project_path). This lets it run with the network off.

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.