Skip to content
算盘 LLM Abacus logo

算盘 LLM Abacus MCP server

Which MCP servers are 算盘 LLM Abacus's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to 算盘 LLM Abacus

Whose server it is
  • Registry namecom.llmabacus/pricingverified in the MCP registry

The registry name sits under llmabacus.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools2
  • Server calls itselfllmabacus
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 102 ms.

Should an agent connect itNot proven either way yet
  • Its tools do Compare per-token prices across listed LLM models, but not Call Claude, GPT and Gemini models through one API; Check model usage rankings on OpenRouter.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • For "Compare per-token prices across listed LLM models", the likely first call is query_model_price.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 5, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it1 of 3 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer416 ms
  • Space in an agent's context≈ 338 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · Compare per-token prices across listed LLM models
  • cannot · Call Claude, GPT and Gemini models through one API
  • cannot · Check model usage rankings on OpenRouter

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-24
  • query_model_price

    查询指定大模型（如 GPT-5, Claude, DeepSeek）的最新 API 输入、输出和缓存输入单价（单位：每百万 tokens）。

  • estimate_cost

    估算一段文本或指定 token 数在某个大模型上的**输入侧**调用成本，以人民币 ¥ 计价。text_or_tokens 支持两种模式：传自然语言文本时自动估算 token 数（中文按字符、英文按词分别计），传纯数字字符串时直接作为已知 token 数使用。返回：所用估算方法、token 数、按原价计的输入成本；若该模型提供缓存输入价，另给出缓存命中成本、相对原价的节省百分比与倍数差价；末尾附该模型的输入 / 输出 / 缓存输入单价（每百万 tokens）。⚠️…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "pricing": {
      "type": "http",
      "url": "https://llmabacus.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http llmabacus https://llmabacus.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://llmabacus.com/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.