Multi-layer codebase analysis with Gemini AI. 4 agents, 5 commands, 3 skills for architecture analysis, pattern detection, and dataflow tracing
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add codebase-analyzer --env GEMINI_API_KEY='<GEMINI_API_KEY>' -- npx -y codebase-analyzer-mcp --mcp~/.codex/config.toml
[mcp_servers.codebase-analyzer]
command = "npx"
args = ["-y", "codebase-analyzer-mcp", "--mcp"]
env = { GEMINI_API_KEY = "<GEMINI_API_KEY>" }
# codex mcp add codebase-analyzer --env GEMINI_API_KEY='<GEMINI_API_KEY>' -- npx -y codebase-analyzer-mcp --mcp~/.cursor/mcp.json
{
"mcpServers": {
"codebase-analyzer": {
"command": "npx",
"args": [
"-y",
"codebase-analyzer-mcp",
"--mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"codebase-analyzer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"codebase-analyzer-mcp",
"--mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"codebase-analyzer": {
"command": "npx",
"args": [
"-y",
"codebase-analyzer-mcp",
"--mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"codebase-analyzer": {
"command": "npx",
"args": [
"-y",
"codebase-analyzer-mcp",
"--mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"codebase-analyzer": {
"command": "npx",
"args": [
"-y",
"codebase-analyzer-mcp",
"--mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}Environment variables
GEMINI_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.