Codegraph runs on your own machine — the client starts it, so there is no endpoint to ping. 697 installs a week from npm. Last commit 13 Sep 2026.
Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.
We read the source, 19 h ago · rules 3dff92dd89df
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.
if (fs.existsSync('/.dockerenv')) return 'container';
postinstall: node bin/postinstall.js
этот файл ставится пользователю, но в репозитории его нет
const child = spawn(binaryPath, args, {
const binaryPath = path.join(binDir, binaryName);
_serverProcess = Process.Start(startInfo);
"**/id_rsa",
__POSTHOG_KEY__: JSON.stringify(process.env.CODEGRAPH_POSTHOG_KEY ?? ''),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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.
claude mcp add codegraph -- npx -y @astudioplus/codegraph-mcp
{
"mcpServers": {
"codegraph": {
"args": [
"-y",
"@astudioplus/codegraph-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.codegraph]
command = "npx"
args = ["-y", "@astudioplus/codegraph-mcp"]
{
"mcpServers": {
"codegraph": {
"args": [
"-y",
"@astudioplus/codegraph-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"codegraph": {
"args": [
"-y",
"@astudioplus/codegraph-mcp"
],
"command": "npx"
}
}
}
Local semantic code graph: source, definitions, callers, callees, impact, and semantic change review
AST-based semantic code search: 33 tools, 35 languages, call tracing, impact analysis
AST-based semantic code search: 39 tools over 37 languages. Call tracing and impact analysis.
Private AI context layer for semantic code search, dependency graphs, memory, and workspaces.
Code intelligence for 15+ languages: semantic graph queries instead of file reads. 37 MCP tools.
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.
Answers built from our own checks of this server.