io.github.lazymac2x/ai-token-counter is an MCP server published by io.github.lazymac2x, hosted at api.lazy-mac.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including count_tokens, estimate_cost, get_model_pricing, list_models.
Cloudflare Workers MCP server: ai-token-counter
160 connections through 5 shared values. Tap any node.
Count tokens for a text string or chat messages array for any supported AI model (GPT-4o, Claude, Gemini, Mistral, Llama).
| Parameter | Type | Description |
|---|---|---|
| text | string | Plain text to count tokens for. |
| model | string | Model ID, e.g. gpt-4o, claude-sonnet-4. Defaults to gpt-4o. |
| messages | array | Chat messages array in OpenAI/Anthropic format. |
{
"name": "count_tokens",
"description": "Count tokens for a text string or chat messages array for any supported AI model (GPT-4o, Claude, Gemini, Mistral, Llama).",
"inputSchema": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Plain text to count tokens for."
},
"model": {
"type": "string",
"description": "Model ID, e.g. gpt-4o, claude-sonnet-4. Defaults to gpt-4o."
},
"messages": {
"type": "array",
"items": {
"type": "object"
},
"description": "Chat messages array in OpenAI/Anthropic format."
}
}
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Estimate the cost of an AI API call given model and token counts or text. Returns input/output/total cost and optional monthly projection.
| Parameter | Type | Description |
|---|---|---|
| text | string | Text to tokenize for input (if input_tokens not given). |
| model * | string | Model ID, e.g. gpt-4o, claude-opus-4, gemini-2.0-flash. |
| input_tokens | integer | Number of input tokens. |
| output_tokens | integer | Number of output tokens. |
| requests_per_day | number | If given, adds daily/monthly/yearly cost projection. |
{
"name": "estimate_cost",
"description": "Estimate the cost of an AI API call given model and token counts or text. Returns input/output/total cost and optional monthly projection.",
"inputSchema": {
"type": "object",
"required": [
"model"
],
"properties": {
"text": {
"type": "string",
"description": "Text to tokenize for input (if input_tokens not given)."
},
"model": {
"type": "string",
"description": "Model ID, e.g. gpt-4o, claude-opus-4, gemini-2.0-flash."
},
"input_tokens": {
"type": "integer",
"description": "Number of input tokens."
},
"output_tokens": {
"type": "integer",
"description": "Number of output tokens."
},
"requests_per_day": {
"type": "number",
"description": "If given, adds daily/monthly/yearly cost projection."
}
}
}
}Get input/output pricing per 1M tokens for a specific AI model.
| Parameter | Type | Description |
|---|---|---|
| model * | string | Model ID, e.g. gpt-4o, claude-haiku-3, llama-3-70b. |
{
"name": "get_model_pricing",
"description": "Get input/output pricing per 1M tokens for a specific AI model.",
"inputSchema": {
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"description": "Model ID, e.g. gpt-4o, claude-haiku-3, llama-3-70b."
}
}
}
}List all supported AI models with their pricing and context windows.
No parameters.
{
"name": "list_models",
"description": "List all supported AI models with their pricing and context windows.",
"inputSchema": {
"type": "object",
"properties": {}
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.