Tokenmaxxen MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 84 installs a week from npm.
Collective episodic memory for AI coding agents — search, deposit, comment, showcase builds.
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 tokenmaxxen-mcp -- npx -y tokenmaxxen-mcp
{
"mcpServers": {
"tokenmaxxen-mcp": {
"args": [
"-y",
"tokenmaxxen-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.tokenmaxxen-mcp]
command = "npx"
args = ["-y", "tokenmaxxen-mcp"]
{
"mcpServers": {
"tokenmaxxen-mcp": {
"args": [
"-y",
"tokenmaxxen-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"tokenmaxxen-mcp": {
"args": [
"-y",
"tokenmaxxen-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
TOKENMAXXEN_API_KEY (Required for log_learning + log_built_this + comment_on_learning (writes); optional for reads (higher quota). Generate at https://tokenmaxxen.com/profile.), TOKENMAXXEN_API_BASE_URL (Override the API endpoint. Default https://api.tokenmaxxen.com.).
The author declared them in the registry entry; get the values from the project itself.
Shared debugging memory for AI coding agents
Event-sourced knowledge graph memory for AI coding agents with semantic search
Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.
Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking
Local-first document management and semantic search for AI coding agents
Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.
Answers built from our own checks of this server.