人口智能 · MCP

把模拟焦点小组，
变成智能体可调用的工具。

AI 智能体可在任务进行中通过 CrowdOS MCP 服务器发起调查，包括 Free 在内的每个套餐均可使用。添加一个 URL，或执行一次 pip install。面板依据人口普查数据抽取，内部意见相左，而不是一个模型的单一意见。

MODEL CONTEXT PROTOCOL·CLAUDE DESKTOP · CURSOR · CLINE·15 个可供智能体调用的工具·PRO 与 MAX 已包含

什么是 MCP

Claude 早已在说的协议

Model Context Protocol（模型上下文协议）是 Anthropic 推出的开放标准，用于把 AI 智能体连接到外部服务。Claude Desktop、Cursor、Cline、Zed，以及不断增加的智能体框架（LangGraph、CrewAI、AutoGPT、Devin）都原生支持它。把一个 MCP 服务器写进宿主程序的配置，它的工具就会出现在模型的工具选择器里——无需胶水代码，也无需为每个应用单独接入 SDK。

CrowdOS 提供两种接入方式：由 API 直接托管的端点，以及面向桌面宿主程序、可用 pip 安装并中继到该端点的 stdio 服务器。两者为你的账户提供同样的工具，并负责请求整形、响应精简与错误脱敏。

HOSTS

LangGraph and CrewAI run the agent. CrowdOS is the crowd.

CrowdOS is the crowd an agent should query. LangGraph and CrewAI are hosts: the place the agent runs. Mount the server and the same tools show up in the model's tool picker. AutoGPT and Devin speak the protocol too, the same way Claude Desktop, Cursor and Cline do.

A PROMPT IS NOT A PANEL

An agent role-playing a panel isn't enough

One model acting like N personas (effectively n=1).

An LLM persona is a costume for one prompt. Ours is a database row: census-grounded people with a fixed identity, an opinion history, and a standing news habit. Query that crowd. Do not ask one model to play the panel.

  • 接入

    托管版：添加一个 URL，无需安装

    URL
    https://api.crowdos.ai/mcp

    MCP 端点由 API 自身提供，因此始终与平台保持同步——没有需要更新的软件包。在 claude.ai（设置 → 连接器）、Cursor，或任何支持远程服务器的客户端中，把它添加为远程 MCP 服务器。支持 OAuth 的客户端会在首次连接时引导你完成登录与授权；该授权会以可撤销的密钥形式出现在 /account/api-keys 下。改用请求头的客户端，则使用 Authorization: Bearer crowd_... 搭配 MCP 密钥。

  • 安装

    自托管：一条 pip，一段配置

    BASH
    pip install crowdos-mcp

    然后在 /account/api-keys 创建一个 MCP 密钥（所有套餐均可创建），并把下面这段粘贴到你的 Claude Desktop 配置文件（~/Library/Application Support/Claude/claude_desktop_config.json）中：

    JSON
    {
  "mcpServers": {
    "crowdos": {
      "command": "crowdos-mcp",
      "env": {
        "CROWDOS_API_KEY": "crowd_..."
      }
    }
  }
}

    Cursor 与 Cline 在各自的 MCP 服务器设置中使用同样的 JSON 结构。重启宿主程序，CrowdOS 的工具就会出现在智能体的工具选择器里。

BY RESEARCH JOB

The same tools, grouped by the question

The list below is every tool the server exposes. These four groups are the research jobs an agent is usually hired for.

  • OPINION

    What do people think?

    run_focus_group is a voting study: a sentiment summary and representative quotes. run_debate is a multi-round debate: convergence and the shift from round to round.

  • CHOICE

    Which option wins?

    compare_options is an A/B/C/D test on text options: a Borda leaderboard and a winner. rank_items is MaxDiff: a rank order with bootstrap rank intervals.

  • PRICING

    What would they pay?

    test_pricing runs a Van Westendorp or Gabor-Granger study: price points and a revenue curve.

  • BUDGET

    What will this study cost?

    preview_cost estimates the cost before the agent commits. It is free to call.

工具

15 个工具，为智能体而设计

  • run_focus_group所有套餐

    情绪倾向 / 投票调查——sentiment_summary 与代表性引述

  • run_debate所有套餐

    多轮模拟辩论——收敛度与每轮立场变化

  • compare_options所有套餐

    对 2–10 个文本选项（套餐上限：Free 3 个，Pro 5 个，Max 10 个）做 A/B/C/D 测试——Borda 排行榜与胜出项

  • test_pricingPRO + MAX

    Van Westendorp / Gabor-Granger 定价调查——价格点与收入曲线

  • rank_itemsPRO + MAX

    对 4–200 个条目做 MaxDiff——排序结果附自助法排名区间

  • pretest_questions企业版

    预测试 1–40 道问卷草稿题目——正式投放前给出逐题结论

  • estimate_reach所有套餐

    预览 custom_audience 筛选条件所描述的受众有多宽——免费

  • preview_cost所有套餐

    正式提交前估算费用与耗时——智能体在这里做预算

  • list_demographic_presets所有套餐

    查看可用的受众模板

  • get_simulation所有套餐

    获取此前已运行调查的完整结果

  • cancel_simulation所有套餐

    停止运行中的调查并释放预留额度

  • crowd_sample所有套餐

    浏览实时的智能体人群（已脱敏）

  • list_panels企业版

    已保存的面板（由 persist_panel / evolve_panel 运行创建）— 仅元数据，最新在前

  • get_panel企业版

    单个已保存面板 — 规模、到期时间、人口构成、已记录的会话（不含受访者名单）

  • delete_panel企业版

    删除你拥有的已保存面板 — 立即且永久

preview_cost 是大多数智能体最容易忽略的一个——在任何样本量超过 100 的调查之前先调用它，看清费用（美分）与耗时（秒）的估算，再判断预算是否允许。调用免费。

实际运行

一次智能体调用是什么样子

TEXT
> 就企业是否应强制推行四天工作制运行一次焦点小组。
   使用 us_general_population 中的 200 个智能体。

[tool: preview_cost]   → estimate_cents=400 · ~33-88s
[tool: run_focus_group] → sim ad4b3736…
   sentiment_summary: { positive_pct: 71.5, negative_pct: 18.0,
                        neutral_pct: 10.5 }
   sample_responses: [ Maria Chen "It would be great for ...", ... ]
   billing.actual_cents: 400

智能体先选择 preview_cost，因为样本量并不算小；确认 4.00 美元在可承受范围内后，才提交 run_focus_group。精简后的响应（情绪汇总 + 5 条代表性引述 + 计费信息）足以放进上下文；若智能体需要每一位受访者的完整推理，可用 get_simulation 拉取完整数据。

ACCURACY

The opinion benchmark, published

On the Pew opinion benchmark, the crowd's opinion distribution matches published polling at 93.3% parity, with a mean absolute error of 3.36 percentage points and a Pearson r of 0.984. That published figure is the opinion benchmark. Creative ranking and in-market ad performance are measured separately.

费用

所有套餐均可使用

MCP 适用于所有套餐，包括 Free。调查按与网页端相同的单受访者费率从账户余额中扣减——一次小型焦点小组约 0.40 美元。

样本组上限与网页端一样跟随套餐：Free 最多 20 位受访者，Pro 500 位，Max 1,000 位；每分钟请求数分别为 5、30、120 次，每月 MCP 消费上限分别为 $5、$500、$2,500。价格 →

每次 run_focus_group / run_debate 的响应都包含 billing.actual_cents 字段，便于智能体自行累计花费。

框架

REST API 面向企业版账户

想从自己的代码而不是智能体宿主程序调用 CrowdOS？REST API 面向企业版账户开放。企业版 → LangGraph 与 CrewAI 都有社区维护的 MCP 桥接包，无需运行 MCP 宿主程序，即可把我们的服务器挂载到框架智能体中。

WHERE THIS FITS

The same crowd, in the browser

The MCP server is the way an agent runs a focus group. Pulse is a vote, a debate or a comparison. Screening Room pressure-tests a creative, a concept or a deck before you ship. Ads Labo reads which of two to four ad variants a panel prefers.

FAQ

What is a focus group MCP server?

A focus group MCP server is a Model Context Protocol endpoint an AI agent can call. CrowdOS speaks it two ways: a hosted endpoint the API serves directly, and a pip-installable server for desktop hosts. Both offer the same tools for your account. Claude Desktop, Cursor, Cline, Zed, LangGraph, CrewAI, AutoGPT and Devin speak the protocol. Drop the server into the host's config and its tools show up in the model's tool picker.

Does it work with Claude, Cursor and Cline?

Yes. Claude Desktop, Cursor and Cline speak Model Context Protocol natively. Cursor and Cline use the same JSON shape in their MCP-server settings. Restart the host and the CrowdOS tools appear in the agent's tool picker.

How is CrowdOS different from LangGraph or CrewAI?

CrowdOS is the crowd an agent should query. LangGraph and CrewAI are hosts: the place the agent runs. LangGraph and CrewAI have community MCP-bridge packages that let you mount the CrowdOS server into a framework agent without running an MCP host.

Why not prompt an agent to role-play a panel?

One model acting like N personas (effectively n=1). An LLM persona is a costume for one prompt. Ours is a database row: census-grounded people with a fixed identity, an opinion history, and a standing news habit. Query that crowd. Do not ask one model to play the panel.

How accurate is the crowd an agent queries?

On the Pew opinion benchmark, the crowd's opinion distribution matches published polling at 93.3% parity, with a mean absolute error of 3.36 percentage points and a Pearson r of 0.984. That is the published opinion benchmark. The full ledger is on the benchmarks page. Creative ranking and in-market ad performance are measured separately.

30 秒拿到你的 MCP 密钥。

免费注册 →已登录？管理密钥 →