tokentally

endpoint

https://tokentally.mike-tusa.workers.dev/mcp

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is tokentally live?

Yes — it answered the hub's last check (checked 50m ago). It answered 100% of checks over the last 30 days.

Is tokentally free to use?

Yes — the hub reached it with no key and no payment.

What tools does tokentally have?

4 tools: truncate_to_budget, estimate_cost, chunk_text, count_tokens.

Is tokentally safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• truncate_to_budget unknown never probed

  Truncate text to max_tokens (keep start or end) for an encoding or model.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233

  {
    "type": "object",
    "required": [
      "text",
      "max_tokens"
    ],
    "properties": {
      "keep": {
        "enum": [
          "start",
          "end"
        ],
        "type": "string"
      },
      "text": {
        "type": "string",
        "description": "Text (≤256 KB). URLs are not fetched."
      },
      "model": {
        "type": "string"
      },
      "encoding": {
        "enum": [
          "o200k_base",
          "cl100k_base"
        ],
        "type": "string"
      },
      "max_tokens": {
        "type": "integer"
      }
    }
  }

  arguments 33 lines copy
• estimate_cost unknown 50m ago

  Estimate USD cost per model from text or input_tokens plus output_tokens using a dated price table (prices_as_of 2026-10-27). Estimates, not live billing.

  mcp-tool

  123456789101112131415161718192021

  {
    "type": "object",
    "properties": {
      "text": {
        "type": "string",
        "description": "Text (≤256 KB). URLs are not fetched."
      },
      "models": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "input_tokens": {
        "type": "integer"
      },
      "output_tokens": {
        "type": "integer"
      }
    }
  }

  arguments 21 lines copy
• chunk_text unknown 50m ago

  Split text into token-bounded chunks on paragraph/sentence boundaries with character offsets, token counts and optional overlap.

  mcp-tool

  12345678910111213141516171819202122232425262728

  {
    "type": "object",
    "required": [
      "text"
    ],
    "properties": {
      "text": {
        "type": "string",
        "description": "Text (≤256 KB). URLs are not fetched."
      },
      "model": {
        "type": "string"
      },
      "encoding": {
        "enum": [
          "o200k_base",
          "cl100k_base"
        ],
        "type": "string"
      },
      "chunk_tokens": {
        "type": "integer"
      },
      "overlap_tokens": {
        "type": "integer"
      }
    }
  }

  arguments 28 lines copy
• count_tokens unknown 50m ago

  Count tokens for text in o200k_base and cl100k_base side by side, plus approximate Claude/Gemini/Llama counts with method notes. OpenAI counts (o200k_base, cl100k_base) are exact for those tokenizers. Claude, Gemini and Llama counts are APPROXIMATE (proxy encoding; real tokenizers differ, often by 10-20%, and newer Claude tokenizers by ~30% or more). Cost estimates use a dated price table (prices_as_of 2026-10-27) and are estimates, not live billing. Stateless: text is not stored or logged; no URL fetching. Max input is 256 KB. A single unbroken run of characters near that cap may hit a CPU timeout (503); normal text at the cap is supported.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "text"
    ],
    "properties": {
      "text": {
        "type": "string",
        "description": "Text (≤256 KB). URLs are not fetched."
      }
    }
  }

  arguments 12 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.