Perspective AI

Rigid forms cause drop-off, weaken qualification, and strip away context. Perspective uses adaptive AI to capture structured data and trigger automation, so you understand what truly matters to your customers and can make decisions with conviction.

Once connected, your AI assistant can design conversation agents, analyze conversations, deploy embeds, and automate follow-ups directly from Claude Desktop, Claude Code, Cursor, or any MCP-compatible client. Try prompts like:

Design a Concierge that qualifies pricing-page leads by budget and timeline.

Why are people abandoning my lead-capture concierge this week?

Whenever a conversation scores above 80 on trust, push it to HubSpot and ping #sales in Slack.

Add the MCP URL to your client and complete a one-time browser sign-in. Tokens stay out of config files; every connected app shows up underSettings → Connected Appsin your workspace, and you can revoke access anytime.

claude mcp add --transport http perspective https://getperspective.ai/mcp

{ "mcpServers": { "perspective": { "type": "http", "url": "https://getperspective.ai/mcp" } } }

claude mcp add perspective --transport http https://getperspective.ai/mcp --header "Authorization: Bearer YOUR_TOKEN"

{ "mcpServers": { "perspective": { "type": "http", "url": "https://getperspective.ai/mcp", "headers": { "Authorization": "Bearer YOUR_TOKEN" } } } }

For stdio-only clients, usemcp-remotewith an explicitAuthorizationheader:

Once connected, your AI assistant can call the following 22 tools, grouped by lifecycle stage:

- workspace_list: List all workspaces you can access
- workspace_get: Get details for a workspace
- workspace_get_default: Get your default workspace

- perspective_list: List perspectives in a workspace, or search by name across all workspaces
- perspective_get: Get full configuration and stats for a perspective
- perspective_create: Create a new perspective from a natural-language brief
- perspective_respond: Answer a follow-up question during perspective design
- perspective_update: Refine a perspective with natural-language feedback
- perspective_await_job: Long-poll a perspective design job to completion
- perspective_get_preview_link: Get a shareable preview URL for testing before deployment

- perspective_get_embed_options: Get embed snippets (fullpage, widget, popup, slider, float, card) and the SDK reference
- participant_invite: Create 48-hour magic-link invites, optionally sent via email

- perspective_get_stats: Aggregate stats and distributions over a time period
- perspective_list_conversations: List conversations with filters (status, trust score, date)
- perspective_get_conversation: Get full conversation details, including transcript and trust assessment
- perspective_get_conversations: Token-efficient batch fetch of conversations for bulk analysis

- automation_list: List automations on a perspective with status, channel, and metadata
- automation_create: Create an automation (webhook, email, Slack, HubSpot)
- automation_update: Update fields on an existing automation
- automation_delete: Permanently delete an automation
- automation_test: Run an end-to-end test against a mock conversation
- integration_manage: List providers (Slack, HubSpot), connect them, and search their tools

Once installed, ask your AI assistant to drive the full perspective lifecycle: design, deploy, analyze, and automate.

-

Design & iterate. Create any of four conversation agent types:

- "Design a Concierge that qualifies pricing-page leads by budget and timeline. Keep the tone warm, not salesy."
- "Build an Interviewer for churn research. Find out why customers left, what alternatives they chose, and what would have kept them."
- "Spin up an Evaluator for 30-day onboarding feedback. What's working and what's confusing?"
- "Set up an Advocate for our refund policy. Listen first, then explain the process without sounding defensive."

Deploy & distribute. Embed on your site or send personalized invites to specific participants:

- "Give me the popup embed snippet for my concierge and walk me through adding it to our pricing page in Next.js."
- "Invite our 20 design partners to my beta-feedback perspective, and prefill each person's name and email."

Analyze: "Why are people abandoning my lead-capture concierge this week? Pull the drop-off conversations and summarize the top reasons."

Automate: "Whenever a conversation scores above 80 on trust, push it to HubSpot as a contact and ping #sales in Slack."

Outputsperspective.mcpbin the current directory.

Bumps version, commits, tags, and pushes. GitHub Action creates the release.

Interact with capabilities of the CRIC Wuye AI platform, an intelligent assistant specifically for the property management industry.

Agent-native helpdesk — AI agents run support tickets over MCP and pay per action in USDC via x402.

An MCP server that provides an automatic answering function for the Qingma Yizhan platform.

Interact with Arcanna's AI use cases through the Model Context Protocol (MCP).

Invoke task chains on the iFlytek SparkAgent Platform.

The Most Comprehensive ServiceNow AI Toolkit — 400+ MCP tools, 26 AI capabilities, SDK mode, Direct API mode. Covers ITSM, ITOM, CMDB, HRSD, CSM, SecOps, GRC and 35+ modules.

Preloop is an event-driven AI automation platform with built-in human-in-the-loop safety based on MCP proxying.

Give your AI a direct line into your Swell store. Manage products, orders, and customers through natural conversation.

Exposes a Magento 2 store's catalog, cart, checkout, customer, sales and wishlist operations as MCP tools, so an AI agent can search products and build a real cart against the live store.