Token Lens runs on your own machine — the client starts it, so there is no endpoint to ping.
Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.
Today is the operative word: we check Token Lens 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 token-lens -- npx -y @kunal_dutt/token-lens
{
"mcpServers": {
"token-lens": {
"args": [
"-y",
"@kunal_dutt/token-lens"
],
"command": "npx"
}
}
}
[mcp_servers.token-lens]
command = "npx"
args = ["-y", "@kunal_dutt/token-lens"]
{
"mcpServers": {
"token-lens": {
"args": [
"-y",
"@kunal_dutt/token-lens"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"token-lens": {
"args": [
"-y",
"@kunal_dutt/token-lens"
],
"command": "npx"
}
}
}
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
Token-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.
Read your recorded AI agent runs, and what changed when you swapped a model or prompt.
Persistent, consensus-validated institutional memory for AI agents. Runs locally.
Find MCP servers, skills, plugins, agents, prompts and rules for any task.
Model Context Protocol server for awesome-copilot agents and collections
Answers built from our own checks of this server.