Claude Code Usage runs on your own machine — the client starts it, so there is no endpoint to ping. 28 installs a week from npm. Last commit 22 Jun 2026.
Claude Code token usage, cost, and plan limits from local logs and Anthropic's usage API.
Today is the operative word: we check Claude Code Usage every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 claude-code-usage -- npx -y claude-code-usage-mcp
{
"mcpServers": {
"claude-code-usage": {
"args": [
"-y",
"claude-code-usage-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.claude-code-usage]
command = "npx"
args = ["-y", "claude-code-usage-mcp"]
{
"mcpServers": {
"claude-code-usage": {
"args": [
"-y",
"claude-code-usage-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"claude-code-usage": {
"args": [
"-y",
"claude-code-usage-mcp"
],
"command": "npx"
}
}
}
Local-first dashboard + MCP for Claude Code and Codex token usage. Per-MCP/tool breakdown.
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
Claude Code token usage, cost visibility, and SkillFM Beacon AI health checks for MCP agents.
Anthropic Claude Fable 5 MCP server — top-tier planning and code critique for handoff
Read local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.
Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
Answers built from our own checks of this server.