Token Counter is answering right now. Last checked 14 min ago. It exposes 1 tools.
Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
Token Counter does not always answer
Over the last week it answered 48.3% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add token-counter --transport http https://apished.com/mcp/v1/tokens{
"mcpServers": {
"token-counter": {
"url": "https://apished.com/mcp/v1/tokens"
}
}
}[mcp_servers.token-counter]
url = "https://apished.com/mcp/v1/tokens"{
"mcpServers": {
"token-counter": {
"url": "https://apished.com/mcp/v1/tokens"
}
}
}{
"mcpServers": {
"token-counter": {
"url": "https://apished.com/mcp/v1/tokens"
}
}
}Available tools 1
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
tokens_count
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://apished.com/mcp/v1/tokens | streamable-http | answering | 173 ms | 14 min ago |
Alternatives to Token Counter
same job, measured the same wayOPC UA companion spec types, namespace dependencies, and engineering units for AI agents
Local stdio MCP for OpenAI-compatible and Gemini image generation, editing, and model fallback.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
Token-bounded repository context for coding agents over MCP.
OpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.
Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.
Accept-Encoding token count, value discarded
Call every global AI model through one OpenAI-compatible API. One key, all models.
Token Counter — questions
Answers built from our own checks of this server.