mcpbeat Sign in

Code Crawler MCP Server

by nithin554 Your server? Claim it
local only

Code Crawler runs on your own machine — the client starts it, so there is no endpoint to ping. 1 674 installs a week from npm. Last commit 31 Oct 2026.

Static and dynamic call tracing MCP server backed by a SQLite property graph of your codebase

Installs per day peak 1 481 · avg 116 · +387% w/w
a month agotoday
1 674
Installs / week
npm · @nithin554/code-crawler
0
Stars
0 open issues
31 Oct 2026
Last commit
79 releases in 90 days
MIT
License
TypeScript

What the code does

We read the source, 1 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable src/config.ts:64
      if (PROJECT_MARKERS.some((marker) => fs.existsSync(path.join(dir, marker)))) return dir;

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add code-crawler -- npx -y @nithin554/code-crawler
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "code-crawler": {
      "command": "npx",
      "args": [
        "-y",
        "@nithin554/code-crawler"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.code-crawler]
command = "npx"
args = ["-y", "@nithin554/code-crawler"]
.cursor/mcp.json
{
  "mcpServers": {
    "code-crawler": {
      "command": "npx",
      "args": [
        "-y",
        "@nithin554/code-crawler"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "code-crawler": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@nithin554/code-crawler"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: CODECRAWLER_DB (Path to the SQLite graph database (default ~/.code-crawler/index.db)), CODECRAWLER_EXCLUDE_DIRS (Comma-separated directories to skip during crawl), CODECRAWLER_DEFAULT_LIMIT (Default result cap for list queries (default 50)), CODECRAWLER_MAX_DEPTH (Traversal depth cap (default 10)), CODECRAWLER_HELPFUL_ERRORS (Fuzzy suggestions on unknown symbols (default true)).

Alternatives to Code Crawler

same job, measured the same way
Automatised Pipeline
by cdeust

Codebase intelligence MCP server — index any repo into a property graph; 26 tools for agents.

local only
Calm MCP
by eilodon

MCP server giving coding agents a call-graph-aware, hash-verified view of a codebase, not grep.

121 installs/wk local only
crowbar
by kushvinth

Retrieve CVEs and index them inside your codebase. One SQLite+FTS5 index, one CLI, one MCP server.

649 installs/wk local only
Treering
by redholetechnologies

A local map of your codebase over time: symbols, callers, subgraphs and structural change.

local only
Socraticode
by giancarloerra

MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.

2 582 installs/wk local only
phpgraph
by hbenabdallah

Knowledge graph of a PHP codebase by static analysis: calls, routes, buses, layers, impact

local only
Meeba Brain
by meemoprasad

Repository knowledge graph MCP server for codebase understanding and debugging.

5 tools answering
repomap
by sylphxai

A map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.

673 installs/wk local only

Code Crawler — questions

Answers built from our own checks of this server.

Why is there no uptime for Code Crawler?
Code Crawler runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @nithin554/code-crawler was installed 1 674 times last week.
How do I connect Code Crawler?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @nithin554/code-crawler straight from npm; nothing to host, nothing to sign up for.
How many people use Code Crawler?
The npm package @nithin554/code-crawler was installed 1 674 times in the last week. Week over week that is +387%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Code Crawler open source?
Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.