About signal-relay
signal-relay is a remote MCP server connecting AI agents to SocioLogic’s synthetic persona platform for customer research. It supports persona interviews and research campaigns, with tools for focus groups, web research, and report exports.
Key features
- 01Access synthetic customer personas
- 02Create and run multi-persona campaigns
- 03Organize personas into focus groups
- 04Search the web and research topics
- 05Export campaign results as PDF or JSON
- 06Retrieve persona memories with semantic search
Use cases
- 01Interview personas about a product concept
- 02Run a campaign with custom research questions
- 03Group personas for cohort-based research
- 04Export campaign findings for a board report
MCP support
It exposes SocioLogic persona, campaign, focus group, web research, and account tools to MCP clients. Clients connect to the hosted remote server or a self-hosted Cloudflare Workers deployment using API-key authentication.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.sociologic.aiclaude mcp add --transport http sociologicai-signal-relay https://mcp.sociologic.ai{"mcpServers":{"sociologicai-signal-relay":{"type":"http","url":"https://mcp.sociologic.ai"}}}Open in Cursor{"servers":{"sociologicai-signal-relay":{"type":"http","url":"https://mcp.sociologic.ai"}}}Open in VS Code{"mcpServers":{"sociologicai-signal-relay":{"type":"http","url":"https://mcp.sociologic.ai"}}}{"mcpServers":{"sociologicai-signal-relay":{"serverUrl":"https://mcp.sociologic.ai"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://mcp.sociologic.aiAuth requiredTools
Details
From the project READMESignal Relay - SocioLogic MCP Server
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.
-
Get an API key at sociologic.ai/dashboard/api-keys (100 free credits on signup)
-
Configure your MCP client:
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"sociologic": {
"transport": "http",
"url": "https://mcp.sociologic.ai",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}
Claude Code (.mcp.json in your project):
{
"mcpServers": {
"sociologic": {
"transport": "http",
"url": "https://mcp.sociologic.ai",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}
- Start chatting! Ask Claude to interview personas, create campaigns, or explore the marketplace.
Self-Hosting
Deploy your own instance to Cloudflare Workers:
Prerequisites
- Node.js v18+
- Cloudflare account (free tier works)
Installation
# Clone the repository
git clone https://github.com/SocioLogicAI/signal-relay.git
cd signal-relay
# Install dependencies
npm install
# Login to Cloudflare
npx wrangler login
# Deploy
npx wrangler deploy
Your server will be available at https://sociologic-mcp-server.<your-subdomain>.workers.dev
Local Development
npm run dev
Starts a local server at http://localhost:8787.
Available Tools
| Tool | Description |
|---|---|
sociologic_list_personas | List synthetic personas from marketplace or private collection |
sociologic_get_persona | Get detailed persona information (demographics, psychographics, traits) |
sociologic_create_persona | Generate a new persona from natural language description |
sociologic_get_persona_memories | Retrieve persona's semantic memories via vector search |
sociologic_list_campaigns | List research campaigns with status and results |
sociologic_get_campaign | Get campaign details including interviews and findings |
sociologic_create_campaign | Create multi-persona research campaign with custom questions |
sociologic_execute_campaign | Execute draft campaign (async background processing) |
sociologic_export_campaign | Export campaign results as PDF or JSON |
sociologic_list_focus_groups | List focus groups for cohort-based research |
sociologic_get_focus_group | Get focus group details with member personas |
sociologic_create_focus_group | Create new focus group to organize personas |
sociologic_add_personas_to_focus_group | Add personas to an existing focus group |
sociologic_get_credits_balance | Check current credits balance and usage |
sociologic_search_web | Search the web and scrape results |
sociologic_research_topic | Research a topic with multiple sources |
API Endpoints
| Endpoint | Method | Description |
|---|---|---|
/ | POST | JSON-RPC 2.0 endpoint for MCP protocol |
/health | GET | Health check (requires API key) |
/info | GET | Server information and available tools |
Example Usage
List Available Personas
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
| Variable | Description | Default |
|---|---|---|
SOCIOLOGIC_API_URL | Backend API URL | https://www.sociologic.ai |
wrangler.toml
[vars]
SOCIOLOGIC_API_URL = "https://www.sociologic.ai"
Security
- API keys are passed via
X-API-Keyheader orAuthorization: Bearerheader - 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:
- Go to Cloudflare Dashboard > Security > WAF > Rate limiting rules
- 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
| Operation | Credits |
|---|---|
| List personas | 1 |
| Get persona | 1 |
| Create persona | 5-50 (by fidelity tier) |
| Interview persona | 1 per message |
| Campaign execution | Varies 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.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Links
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.