Token usage tracker for OpenAI and Claude APIs with MCP support, real-time session tracking, and accurate pricing for 2025 models
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y llm-token-trackerAgent-CoreX intelligently routes which tools from wn01011/llm-token-tracker your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"llm-token-tracker": {
"command": "npx",
"args": [
"-y",
"llm-token-tracker"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add llm-token-trackerAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use wn01011/llm-token-tracker directly without routing
npx -y llm-token-trackerNew to Agent-CoreX? View setup guide →