DuDuClaw runs on your own machine — the client starts it, so there is no endpoint to ping. 1 201 installs a week from npm. Last commit 16 Oct 2026.
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
We read the source, 22 h ago · rules ccca72095570
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
json!({"type":"assistant","message":{"id":"msg_0","model":"grok-4.7","content":[{"type":"tool_use","name":"read_file"},{"type":"tool_use","name":"search_tool;rm -rf /"}],
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.
"https://claude.com/cai/oauth/authorize?code=true&client_id=9d1c250a-e61b-44d9-88ed-5944d1962f5e&response_type=code&redirect_uri=https%3A%2F%2Fplatform.claude.com%2Foauth%2Fcode%2Fcallback&scope=user%3Ainference&code_challenge=FAKECHALLENGEFAKECHALLENGEFAKECHALLEN…
std::path::Path::new("/.dockerenv").exists()
postinstall: node scripts/install.js
execFile(
path: path.join(this.options.dest, entry.name),
child = subprocess.Popen(["/bin/sh", "-c", command], stdout=output, stderr=output, start_new_session=True)
{screen && screen.pass + screen.drop + screen.unavailable > 0 && (
return fs.readdirSync(this.options.dest, { withFileTypes: true }).reduce((prev, entry) => {
let api_url = format!("https://api.telegram.org/bot{token}/{method}");
environment = dict(os.environ)
- /var/run/docker.sock:/var/run/docker.sock
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch DuDuClaw and you get told the day something new turns up.
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 duduclaw -- npx -y duduclaw
{
"mcpServers": {
"duduclaw": {
"args": [
"-y",
"duduclaw"
],
"command": "npx"
}
}
}
[mcp_servers.duduclaw]
command = "npx"
args = ["-y", "duduclaw"]
{
"mcpServers": {
"duduclaw": {
"args": [
"-y",
"duduclaw"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"duduclaw": {
"args": [
"-y",
"duduclaw"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
DUDUCLAW_MCP_API_KEY (Key for the standalone server. Create one with `npx duduclaw mcp init` (prints it once; stored only as a hash).).
The author declared them in the registry entry; get the values from the project itself.
Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.
Self-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
Personal wiki and memory for AI assistants: store, search, and recall structured notes.
Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
MCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.
Self-hosted Obsidian-compatible markdown vault with a web UI and a 63-tool MCP server for AI agents
Answers built from our own checks of this server.