Measured data: Claude Code and the coding-agent market

Measured weekly data on Claude Code and coding agents: costs, plugins, MCP registry, npm, HN, issues

我該用這個嗎

品質與安全性

B
說明品質
96%
結構描述完整度
57%
命名品質
87%
汙染風險
80%
權限相符程度
100%
協定合規性
100%

發現項目(3)

  • HIGHTool poisoning patterns detected
  • LOWTool 'mcp_registry_census' description lacks action verb在 mcp_registry_census 中
  • INFOTool description contains placeholder or incomplete text在 score_idea 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~814Token(工具定義)
~432 B典型回應大小
中等的注意力影響(128k 上下文的 0.64%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "measured-data": {
      "url": "https://agentexchange.work/data/mcp"
    }
  }
}

遠端端點

https://agentexchange.work/data/mcpstreamable-http

它能做什麼

工具清單

工具(8)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢list_datasets

List the measured datasets on agentexchange.work/data (Claude Code cost anatomy, tokens per day, plugin marketplace star sample, MCP registry census, npm MCP-server download sample, Show HN outcomes, issue gap maps, token-reduction tools) with pull dates.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_dataset(name)

Return one dataset as JSON. Names: cost-anatomy, tokens-per-day, plugins-marketplace, mcp-registry, npm-mcp-servers, show-hn-claude-code, issues-gap-map, token-reduction-tools.

輸入結構描述

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false
}
⚪issue_gap_map(repo, limit)

Top open issues by thumbs-up for anthropics/claude-code, openai/codex or google-gemini/gemini-cli: what users ask for loudest that is still open.

輸入結構描述

{
  "type": "object",
  "properties": {
    "repo": {
      "type": "string",
      "enum": [
        "anthropics/claude-code",
        "openai/codex",
        "google-gemini/gemini-cli"
      ]
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 40
    }
  },
  "required": [
    "repo"
  ],
  "additionalProperties": false
}
🟢show_hn_claude_code_stats

Points distribution of every Show HN launch with 'Claude Code' in the title over the last 90 days (count, median, p75, p90, share reaching 50 points, top posts).

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
⚪mcp_registry_census

Full-crawl census of the official MCP registry: unique servers, new servers per day, remote share, share of remote servers with no auth.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟡score_idea(idea)

Score a product idea against LIVE market data: the idea in plain words is turned into a market lookup, comparables are pulled from the directory where it would ship (npm, VS Code, WordPress.org, GitHub, Hacker News, Apify, Hugging Face, MCP registry), newcomers (<=24 months) set the reach, sourced priors give conversion and retention. Returns KILL / PASS / UNKNOWN with the deciding number, month-12 revenue ceiling, months to first dollar, and the comparables with links. Takes ~20 s.

輸入結構描述

{
  "type": "object",
  "properties": {
    "idea": {
      "type": "string",
      "description": "the product idea, price and whether it has a free tier, in plain words (8-300 chars)"
    }
  },
  "required": [
    "idea"
  ],
  "additionalProperties": false
}
⚪github_trending(since, language, date, limit)

GitHub Trending (which has no official API or history): today's list, this week, this month, or a language's daily list; or a past day's snapshot by date. Scraped daily and archived.

輸入結構描述

{
  "type": "object",
  "properties": {
    "since": {
      "type": "string",
      "enum": [
        "daily",
        "weekly",
        "monthly"
      ]
    },
    "language": {
      "type": "string",
      "enum": [
        "python",
        "typescript",
        "javascript",
        "go",
        "rust",
        "java",
        "c++",
        "shell"
      ]
    },
    "date": {
      "type": "string",
      "description": "YYYY-MM-DD of an archived snapshot"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "additionalProperties": false
}
🟢claude_code_cost_anatomy

Measured anatomy of 160 real Claude Code sessions: cache-read share of billed context, oversized tool-output share, and the replay effect of capping tool results at 8,000 characters.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本8 個工具
已驗證未記錄版本7 個工具