By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add ast -- uv sync~/.codex/config.toml
[mcp_servers.ast]
command = "uv"
args = ["sync"]
# codex mcp add ast -- uv sync~/.cursor/mcp.json
{
"mcpServers": {
"ast": {
"command": "uv",
"args": [
"sync"
]
}
}
}.vscode/mcp.json
{
"servers": {
"ast": {
"type": "stdio",
"command": "uv",
"args": [
"sync"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"ast": {
"command": "uv",
"args": [
"sync"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"ast": {
"command": "uv",
"args": [
"sync"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"ast": {
"command": "uv",
"args": [
"sync"
]
}
}
}