Skip to content

Measured data: Claude Code and the coding-agent market

by agentexchange.work · remote · no sign-in to list tools · v1.0.0 · published by work.agentexchange

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

Changes · 5
CompareRegistry entry

8 tools: 5 change things and 3 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http measured-data https://agentexchange.work/data/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

8 tools

Changes things 5Claude Code: ask
  • claude_code_cost_anatomyMeasured 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 character…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • issue_gap_mapTop 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • mcp_registry_censusFull-crawl census of the official MCP registry: unique servers, new servers per day, remote share, share of remote servers with no auth.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Full-crawl census of the official MCP registry: unique servers, new servers per day, remote share, share of remote servers with no auth.
  • score_ideaScore 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, …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
Only reads 3Claude Code: allow
  • get_datasetReturn one dataset as JSON.No findings

    Why it is in this group

    • The name "get_dataset" says "get": a word for reading.
    Description, as the server wrote it
    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.
  • list_datasetsList 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…No findings

    Why it is in this group

    • The name "list_datasets" says "list": a word for reading.
    Description, as the server wrote it
    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.
  • show_hn_claude_code_statsPoints 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).No findings

    Why it is in this group

    • The name "show_hn_claude_code_stats" says "show": a word for reading.
    Description, as the server wrote it
    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).

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http measured-data https://agentexchange.work/data/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__measured-data__list_datasets",
      "mcp__measured-data__get_dataset",
      "mcp__measured-data__show_hn_claude_code_stats"
    ],
    "ask": [
      "mcp__measured-data__issue_gap_map",
      "mcp__measured-data__mcp_registry_census",
      "mcp__measured-data__score_idea",
      "mcp__measured-data__github_trending",
      "mcp__measured-data__claude_code_cost_anatomy"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as measured-data. Review it before you use it.