Codebase analysis MCP server for AI agents: complexity metrics, size thresholds, prop drilling, and code smell detection built on tree-sitter and tokei.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add scopewalker -- npx -y scopewalker-mcp~/.codex/config.toml
[mcp_servers.scopewalker]
command = "npx"
args = ["-y", "scopewalker-mcp"]
# codex mcp add scopewalker -- npx -y scopewalker-mcp~/.cursor/mcp.json
{
"mcpServers": {
"scopewalker": {
"command": "npx",
"args": [
"-y",
"scopewalker-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"scopewalker": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"scopewalker-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"scopewalker": {
"command": "npx",
"args": [
"-y",
"scopewalker-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"scopewalker": {
"command": "npx",
"args": [
"-y",
"scopewalker-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"scopewalker": {
"command": "npx",
"args": [
"-y",
"scopewalker-mcp"
]
}
}
}