Signal Relay

io.github.SocioLogicAI由 GitHub 帳號 SocioLogicAI 發布v2.0.0更新於 Nov 2, 2026

Connect AI agents to SocioLogic's synthetic persona platform for market research.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取資料與分析商業與電商

概覽

AI 產生的概覽

將助理連接到 SocioLogic 的合成人物平台，可訪談 AI 人物、執行研究專案並匯出報告。

可以做什麼
  • 瀏覽、檢視並建立合成人物，並擷取其語意記憶
  • 建立、執行並匯出多人物研究專案，支援 PDF 或 JSON 輸出
  • 將人物組成焦點小組並加入成員
  • 搜尋網路並跨多個來源研究主題
  • 查詢點數餘額與用量
適用情境
適合需要模擬顧客人物提供市場調查式回饋，或想在聊天用戶端中執行並匯出多人物訪談專案、而不必使用 SocioLogic 後台的場合。
執行需求
需要 SocioLogic 帳號與 API 金鑰，透過 X-API-Key 標頭（或 Bearer 權杖）傳送。建議使用託管端點；自架需 Node.js 18+ 與 Cloudflare 帳號。各項操作會消耗點數。
安裝前請注意
操作會消耗點數：列出與取得各 1 點，建立人物 5-50 點，訪談每則訊息 1 點，專案執行依規模計，免費額度之外可能產生費用。API 金鑰屬機密，經標頭傳送。建立人物、專案與焦點小組會將資料寫入你的 SocioLogic 帳號，請求會轉送至 SocioLogic API。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Signal Relay，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.SocioLogicAI%2Fsignal-relay/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "signal-relay": {
      "type": "http",
      "url": "https://mcp.sociologic.ai/"
    }
  }
}

README

Signal Relay - SocioLogic MCP Server

[License: MIT] [MCP]

A remote MCP (Model Context Protocol) server that connects AI agents to SocioLogic's synthetic persona platform. Interview realistic customer personas, run multi-persona research campaigns, and export board-ready reports—all through natural conversation.

Features

  • 24 MCP Tools - Personas, campaigns, focus groups, web research, RNG, credits, and payments
  • High-Fidelity Personas - Synthetic personas with consistent demographics, psychographics, and behavior
  • Semantic Memory - RAG-powered memory retrieval for persona continuity across conversations
  • Edge Deployed - Runs on Cloudflare Workers (300+ locations, <50ms latency)
  • Secure - API key authentication, request validation, no data stored on edge

Quick Start

Use the Hosted Server (Recommended)

The fastest way to get started is using our hosted server at https://mcp.sociologic.ai.

  1. Get an API key at sociologic.ai/dashboard/api-keys (100 free credits on signup)

  2. Configure your MCP client:

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

json
{  "mcpServers": {    "sociologic": {      "transport": "http",      "url": "https://mcp.sociologic.ai",      "headers": {        "X-API-Key": "YOUR_API_KEY"      }    }  }}

Claude Code (.mcp.json in your project):

json
{  "mcpServers": {    "sociologic": {      "transport": "http",      "url": "https://mcp.sociologic.ai",      "headers": {        "X-API-Key": "YOUR_API_KEY"      }    }  }}
  1. Start chatting! Ask Claude to interview personas, create campaigns, or explore the marketplace.

Self-Hosting

Deploy your own instance to Cloudflare Workers:

Prerequisites

Installation

bash
# Clone the repositorygit clone https://github.com/SocioLogicAI/signal-relay.gitcd signal-relay
# Install dependenciesnpm install
# Login to Cloudflarenpx wrangler login
# Deploynpx wrangler deploy

Your server will be available at https://sociologic-mcp-server.<your-subdomain>.workers.dev

Local Development

bash
npm run dev

Starts a local server at http://localhost:8787.

Available Tools

ToolDescription
sociologic_list_personasList synthetic personas from marketplace or private collection
sociologic_get_personaGet detailed persona information (demographics, psychographics, traits)
sociologic_create_personaGenerate a new persona from natural language description
sociologic_get_persona_memoriesRetrieve persona's semantic memories via vector search
sociologic_list_campaignsList research campaigns with status and results
sociologic_get_campaignGet campaign details including interviews and findings
sociologic_create_campaignCreate multi-persona research campaign with custom questions
sociologic_execute_campaignExecute draft campaign (async background processing)
sociologic_export_campaignExport campaign results as PDF or JSON
sociologic_list_focus_groupsList focus groups for cohort-based research
sociologic_get_focus_groupGet focus group details with member personas
sociologic_create_focus_groupCreate new focus group to organize personas
sociologic_add_personas_to_focus_groupAdd personas to an existing focus group
sociologic_get_credits_balanceCheck current credits balance and usage
sociologic_search_webSearch the web and scrape results
sociologic_research_topicResearch a topic with multiple sources

API Endpoints

EndpointMethodDescription
/POSTJSON-RPC 2.0 endpoint for MCP protocol
/healthGETHealth check (requires API key)
/infoGETServer information and available tools

Example Usage

List Available Personas

bash
curl -X POST https://mcp.sociologic.ai/ \  -H "Content-Type: application/json" \  -H "X-API-Key: YOUR_API_KEY" \  -d '{    "jsonrpc": "2.0",    "id": 1,    "method": "tools/call",    "params": {      "name": "sociologic_list_personas",      "arguments": {        "visibility": "public",        "per_page": 10      }    }  }'

Configuration

Environment Variables

VariableDescriptionDefault
SOCIOLOGIC_API_URLBackend API URLhttps://www.sociologic.ai

wrangler.toml

toml
[vars]SOCIOLOGIC_API_URL = "https://www.sociologic.ai"

Security

  • API keys are passed via X-API-Key header or Authorization: Bearer header
  • Request size limited to 1MB to prevent DoS
  • Input validation via Zod schemas on all tool parameters
  • No data stored on edge - all data flows through to the SocioLogic API

Rate Limiting

For production deployments, we recommend enabling Cloudflare's rate limiting:

  1. Go to Cloudflare Dashboard > Security > WAF > Rate limiting rules
  2. Create a rule: 100 requests per 10 seconds per IP

Architecture

┌─────────────────┐      ┌─────────────────────┐      ┌─────────────────┐│                 │      │                     │      │                 ││   MCP Client    │─────▶│  Cloudflare Worker  │─────▶│  SocioLogic API ││  (Claude, etc)  │      │   (This Server)     │      │                 ││                 │◀─────│                     │◀─────│                 │└─────────────────┘      └─────────────────────┘      └─────────────────┘        │                         │                          │        │    MCP Protocol         │    REST API              │        │    (JSON-RPC 2.0)       │    (HTTPS)               │        └─────────────────────────┴──────────────────────────┘

Pricing

OperationCredits
List personas1
Get persona1
Create persona5-50 (by fidelity tier)
Interview persona1 per message
Campaign executionVaries by size

Free tier: 100 credits on signup. See sociologic.ai/pricing for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Links

來源：README.md，提交 2f21229

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v2.0.0最新Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分