Universal Brute Workpack runs on your own machine — the client starts it, so there is no endpoint to ping.
Stdio-first Agent MCP workpack for local tools, audit chains, search, memory, and pipelines.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 universal-brute-workpack -- npx -y universal-brute-workpack
{
"mcpServers": {
"universal-brute-workpack": {
"args": [
"-y",
"universal-brute-workpack"
],
"command": "npx"
}
}
}
[mcp_servers.universal-brute-workpack]
command = "npx"
args = ["-y", "universal-brute-workpack"]
{
"mcpServers": {
"universal-brute-workpack": {
"args": [
"-y",
"universal-brute-workpack"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"universal-brute-workpack": {
"args": [
"-y",
"universal-brute-workpack"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
UBW_CONFIG (Optional path to a custom Universal Brute Workpack config JSON.), UBW_PROFILES (Optional path to a custom profile and deny-list JSON.), UBW_ROOTS (Optional semicolon-separated filesystem roots for local file tools.), TAVILY_API_KEY (Optional Tavily key for search.web before fallback providers.), EXA_API_KEY (Optional Exa key for search.web before fallback providers.), UBW_MEMORY_URL (Optional memory or vector service endpoint for memory.search.), LLM_BASE_URL (Optional OpenAI-compatible base URL for Agent tasks.), LLM_API_KEY (Optional model API key for Agent tasks.), LLM_MODEL (Optional model name for Agent tasks.).
The author declared them in the registry entry; get the values from the project itself.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.
Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.
Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.
Local-first persistent memory MCP server for AI coding agents.
Persistent memory for AI agents with rollback, audit trails, and semantic search.
Answers built from our own checks of this server.