focxle — what your AI agents cost runs on your own machine — the client starts it, so there is no endpoint to ping. 135 installs a week from pypi. Last commit 10 Aug 2026.
Ask what your AI agents cost. Per agent, across every vendor, from your editor.
We read the source, 23 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.
module = __import__(path, fromlist=["BaseCallbackHandler"])
with open(os.path.join(directory, name), "r", encoding="utf-8-sig") as fh:
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 spend -- uvx focxle
{
"mcpServers": {
"spend": {
"args": [
"focxle"
],
"command": "uvx"
}
}
}
[mcp_servers.spend]
command = "uvx"
args = ["focxle"]
{
"mcpServers": {
"spend": {
"args": [
"focxle"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"spend": {
"args": [
"focxle"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
FOCXLE_NO_HISTORY (Set to 1 to stop focxle keeping any local spend history. The server then has nothing to read and will say so.).
The author declared them in the registry entry; get the values from the project itself.
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Kill switch + spend guard for AI agents that spend money, across every wallet vendor at once.
Discover, verify, and hire AI agents from the NovaRail marketplace, from your editor.
Persistent memory layer for AI coding agents — your agent remembers what you taught it.
Debug a bad AI-agent run from your editor: which intent fails, at which step, and why.
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
MCP server for soul.md — your portable AI identity layer across every LLM.
Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.
Answers built from our own checks of this server.