Mmcp.market

Token Counter MCP server

by apished.com·com.apished/token-counter·v1.0.0
No reviews yet

Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.

?
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
?

not scanned yet

Adoption
Not measured yet

Usage numbers are collected on the next scan

Reviews

Write one

Nobody has reviewed Token Counter yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Token Counter tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Not scanned yet. New registry listings are scanned within a day of import.

Install directly

claude mcp add --transport http token-counter https://apished.com/mcp/v1/tokens
Add to Cursor

Token Counter: common questions

Is Token Counter MCP server safe?
Not known yet: the safety scan has not run. New listings are scanned within a few days.
How do I install Token Counter?
It runs remotely at apished.com. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Token Counter need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Token Counter maintained?
The latest release is v1.0.0.
Is Token Counter up?
100% of our last 6 checks got an answer. We check remote servers about four times a day.
What can I use instead of Token Counter?
Servers from other publishers that do the same job: freellmpool MCP server, BridgeNode MCP server and Local Delegate MCP server. Compare all Token Counter alternatives.

Alternatives to Token Counter

Same job from other publishers: the closest match first, then the best rated.

All Token Counter alternatives →
  • freellmpool
    OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
    A
  • BridgeNode MCP
    BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.
    A
  • Local Delegate
    Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
    B
  • mcptoon
    MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).
    A
  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A

More from apished.com →