@Perspective-AI
基本情報
MCP server for Perspective AI. An AI Concierge replaces static forms with adaptive AI conversations that understand real situations, structure key information automatically, and trigger the right next step.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"perspective": {
"command": "npx",
"args": [
"mcp-remote",
"https://getperspective.ai/mcp",
"--header",
"Authorization: Bearer <Token from https://getperspective.ai/settings/mcp>"
]
}
}
}List all your workspaces
Get workspace details
Get your default workspace
List perspectives in a workspace
Get perspective configuration
Create a new perspective from a natural-language description
Answer a follow-up question during creation
Refine a perspective with natural-language feedback
Get a preview link for testing before deployment
Get embed snippets (fullpage, widget, popup, slider, float, card)
Create magic-link invites, optionally sent via email
Aggregate stats and distributions over a time period
List conversations with filters (status, trust score, date)
Get full conversation details
Batch retrieve multiple conversations
Create, list, update, delete, toggle, or test automations (webhook, email, Slack, HubSpot)
List available providers (Slack, HubSpot), connect them, and search their tools
Perspective AI is an MCP server that lets AI assistants design, deploy, analyze, and automate adaptive AI conversation agents (Interviewer, Concierge, Evaluator, Advocate). It replaces static forms with conversational flows that capture structured data and trigger automated follow-ups. It's built for teams using Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP-compatible client.
Install the server via a one-click .mcpb bundle on Claude Desktop, or manually configure any MCP client with the remote HTTP endpoint https://getperspective.ai/mcp plus a bearer token from your Perspective AI settings. Once connected, use natural-language prompts to create agents, analyze conversations, deploy embeds, and set up automations.
You can create four agent types: Interviewer (scales qualitative interviews), Concierge (replaces forms with conversational flow), Evaluator (turns surveys into conversations), and Advocate (listens first, then responds on behalf of a position or brand).
Go to your Perspective AI Settings at `getperspective.ai/settings/mcp`, generate a token, and paste it when prompted during installation.
It supports Claude Desktop (via one-click `.mcpb` install), Claude Code, Cursor, Windsurf, and any MCP client that can connect to a remote HTTP endpoint with a bearer token.
All traffic is TLS-encrypted. Your token is sent only in the `Authorization` header to `https://getperspective.ai/mcp`. Conversation data stays inside your Perspective AI workspace, and this package does not store or cache responses locally.
Yes, you can generate, rotate, or revoke tokens at any time from `getperspective.ai/settings/mcp`.
Hindsight: Agent Memory That Learns
Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
🚀 The fast, Pythonic way to build MCP servers and clients.
A search tool helps dev to solve the naming things problem.
コメント