Skip to main content
Glama
GymCam Analytics

GymCam Analytics

by axelfreeman

GymCam Analytics

GymCam 将健身房已有的摄像头转化为自动出勤与教练绩效分析——无需新硬件,无需签到。

接入现有的 CCTV 视频流和课程表;它能识别教练、统计每节课的到场人数,并报告实际情况:哪些课满员,哪些课冷清,哪些教练能坐满教室。

为什么

健身房老板靠直觉经营。预订软件(Mindbody、Glofox)只能捕捉签到记录——而人们会跳过签到,所以数据不完整。硬件人流量计数器(Density、V-Count)花费数千美元,却只能数人头而没有上下文。

GymCam 复用场馆已有的设备,并将人数统计映射到课程和教练——这才是真正驱动营收的因素。

Related MCP server: Iridium MCP Server

报告内容

  • 今日概览 — 已开课程、总出勤人数、热门课程

  • 教练出勤 — 每位教练的日/周满课率和缺席率

  • 课程表现 — 所有课程按满课率排名,冷门课程一目了然

  • 营收洞察 — 最赚钱与最不赚钱的课程对比

安装

一条命令,直接从此仓库安装(需要 uv):

uvx --from git+https://github.com/axelfreeman/gymcamanalytics gymcam

连接到你的 AI 代理

同样的命令,每个客户使用不同的配置文件。

Claude Desktop(claude_desktop_config.json):

{"mcpServers": {"gymcam": {"command": "uvx", "args": ["--from", "git+https://github.com/axelfreeman/gymcamanalytics", "gymcam"]}}}

Codex(~/.codex/config.toml):

[mcp_servers.gymcam]
command = "uvx"
args = ["--from", "git+https://github.com/axelfreeman/gymcamanalytics", "gymcam"]

Cursor(.cursor/mcp.json)和 Windsurf(~/.codeium/windsurf/mcp_config.json)使用与 Claude Desktop 相同的 JSON 配置块。

Claude Code:

claude mcp add gymcam -- uvx --from git+https://github.com/axelfreeman/gymcamanalytics gymcam

API 密钥

工具需要 API 密钥。在 https://gymcamanalytics.com/get-key 免费获取一个(100 次免费查询,无需信用卡),然后进行设置:

export GYMCAM_API_KEY=your_key_here

工具

工具

返回内容

get_today_summary

已开课程、总出勤人数、热门课程

get_trainer_attendance

教练的满课率 + 缺席次数(日/周)

get_class_performance

按满课率排名的课程

get_revenue_insights

最赚钱与冷门课程对比

状态

预发布阶段。MCP 服务器和工具模式已上线;在您的健身房摄像头接入之前,工具返回示例数据。注册 获取访问权限。

许可证

MIT © 2026 Axel Freeman

Available Tools

4 tools
get_class_performanceB

Rank classes by fill rate: popular vs. dead classes to cut.

Inputs: limit.

get_revenue_insightsA

Most profitable vs. least profitable classes by revenue.

Inputs: no named parameters.

get_today_summaryB

Daily attendance summary: classes held, total attendance, top classes.

Inputs: gym_id.

get_trainer_attendanceC

Attendance and fill-rate for a trainer over 'day' or 'week'.

Inputs: trainer (required), period.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct analytics dimension: daily summary, trainer-specific metrics, class performance, and revenue. No two tools overlap in purpose or output, so an agent can clearly select the right tool for a given request.

    Naming Consistency5/5

    All tools follow a uniform 'get_<noun>_<noun>' pattern (e.g., get_today_summary, get_trainer_attendance). The naming is consistent, descriptive, and predictable, making it easy to infer tool purpose from the name alone.

    Tool Count5/5

    With only 4 tools, the server is tightly scoped to core gym analytics. Each tool provides a distinct slice of the domain without redundancy, and the count is appropriate for a focused analytics service.

    Completeness4/5

    The toolset covers the primary analytics needs: overall summary, trainer performance, class performance, and revenue. Minor gaps exist (e.g., no member-specific analytics or custom date-range queries), but the current surface handles common use cases well.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers