CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Perspective AI

perspective-ai/mcp
22 toolsHTTPregistry active
Summary

Connects Claude to Perspective AI's conversational form platform. You get 22 tools that let you design adaptive conversation agents (interviewer, concierge, evaluator, advocate types), analyze transcripts and trust scores, manage embed deployments, and wire up automations to Slack, HubSpot, or webhooks. The design flow is conversational: describe what you want to capture, refine with natural language, grab a preview link, then push live. Especially useful if you're replacing static forms with AI-driven qualification flows and want to iterate on conversation logic or route high-intent leads without leaving your editor. Authentication via OAuth or personal access token.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Tools

Public tool metadata for what this MCP can expose to an agent.

22 tools
workspace_listLists every workspace the user can access, with workspace_id, uniqueName (slug), and display name. Behavior: - Read-only. Page size 20, sorted by name. Pass nextCursor back as cursor to fetch the next page. - Optional search matches against name, uniqueName (slug), member emai...2 params

Lists every workspace the user can access, with workspace_id, uniqueName (slug), and display name. Behavior: - Read-only. Page size 20, sorted by name. Pass nextCursor back as cursor to fetch the next page. - Optional search matches against name, uniqueName (slug), member emai...

Parameters* required
cursorstring
Pagination cursor from previous response
searchstring
Case-insensitive match against name, uniqueName (slug), member emails, and website
workspace_getReturns details for a single workspace by id or uniqueName (slug): name, plan, and member count. Behavior: - Read-only. - Errors when the workspace does not exist or you do not have access. - Accepts either workspace_id or uniqueName (slug). - Does NOT report whether this work...1 params

Returns details for a single workspace by id or uniqueName (slug): name, plan, and member count. Behavior: - Read-only. - Errors when the workspace does not exist or you do not have access. - Accepts either workspace_id or uniqueName (slug). - Does NOT report whether this work...

Parameters* required
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list)
workspace_get_defaultReturns the user's default workspace (id, uniqueName, name) so you can use it as the `workspace_id` argument for other tools without prompting. Behavior: - Read-only. Takes no parameters. - Picks the default by priority: explicit user default > first owned workspace with activ...

Returns the user's default workspace (id, uniqueName, name) so you can use it as the `workspace_id` argument for other tools without prompting. Behavior: - Read-only. Takes no parameters. - Picks the default by priority: explicit user default > first owned workspace with activ...

No parameter schema in public metadata yet.

perspective_listLists perspectives — either browsing one workspace or searching by name/title across every workspace the user can access. Items include perspective_id, name, title, status, conversation count, and workspace info. Behavior: - Read-only. - Browse mode (workspace_id, no query): l...3 params

Lists perspectives — either browsing one workspace or searching by name/title across every workspace the user can access. Items include perspective_id, name, title, status, conversation count, and workspace info. Behavior: - Read-only. - Browse mode (workspace_id, no query): l...

Parameters* required
querystring
Search by name or title. Enables cross-workspace search.
cursorstring
Pagination cursor from previous response
workspace_idstring
Optional: workspace to list from. Required for browse mode, optional for search mode.
perspective_getReturns the full configuration for one perspective: prompt/setup, outline, structured-output fields, status, basic stats, and the preview/share/direct URLs. Behavior: - Read-only. - Errors when the workspace or perspective is not found or you do not have access. - Stats here a...2 params

Returns the full configuration for one perspective: prompt/setup, outline, structured-output fields, status, basic stats, and the preview/share/direct URLs. Behavior: - Read-only. - Errors when the workspace or perspective is not found or you do not have access. - Stats here a...

Parameters* required
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (from perspective_list or perspective_create)
perspective_get_preview_linkReturns a shareable URL that opens the perspective in preview mode, so you (or a teammate) can have a sample conversation with it before deploying. Behavior: - Read-only. The same stable preview URL every time for a given perspective; the link does not expire. - Conversations...2 params

Returns a shareable URL that opens the perspective in preview mode, so you (or a teammate) can have a sample conversation with it before deploying. Behavior: - Read-only. The same stable preview URL every time for a given perspective; the link does not expire. - Conversations...

Parameters* required
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (from perspective_list or perspective_create)
perspective_get_statsReturns aggregate conversation counts and breakdowns for a perspective over a chosen window (7d, 30d, 90d, or all). Includes totals, completion rate, average duration, plus distributions by period, trust score band, and status. Behavior: - Read-only. - Errors when the perspect...3 params

Returns aggregate conversation counts and breakdowns for a perspective over a chosen window (7d, 30d, 90d, or all). Includes totals, completion rate, average duration, plus distributions by period, trust score band, and status. Behavior: - Read-only. - Errors when the perspect...

Parameters* required
periodstring
Time period: 7d, 30d, 90d, or allone of 7d · 30d · 90d · alldefault: 30d
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (from perspective_list or perspective_create)
perspective_get_embed_optionsReturns the deployment artifacts for a perspective: the share_url and direct_url for outreach plus ready-to-paste embed snippets (fullpage, widget, popup, slider, float, card) and an SDK reference (script URL, events, URL/brand/theme params, JS API methods, callbacks). Behavio...2 params

Returns the deployment artifacts for a perspective: the share_url and direct_url for outreach plus ready-to-paste embed snippets (fullpage, widget, popup, slider, float, card) and an SDK reference (script URL, events, URL/brand/theme params, JS API methods, callbacks). Behavio...

Parameters* required
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (from perspective_list or perspective_create)
perspective_list_conversationsLists conversations for a perspective, with optional filters by status, trust score range, and date range. Each item includes conversation_id, status, structured-output fields, trust score, and a transcript URL. Behavior: - Read-only. - Errors when the perspective is not found...8 params

Lists conversations for a perspective, with optional filters by status, trust score range, and date range. Each item includes conversation_id, status, structured-output fields, trust score, and a transcript URL. Behavior: - Read-only. - Errors when the perspective is not found...

Parameters* required
cursorstring
Pagination cursor from previous response
statusstring
Filter by conversation statusone of completed · partial · abandoned · in_progress
date_tostring
Filter to date (ISO 8601)
date_fromstring
Filter from date (ISO 8601)
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (from perspective_list or perspective_create)
trust_score_maxnumber
Maximum trust score (0-100)
trust_score_minnumber
Minimum trust score (0-100)
perspective_get_conversationReturns the full record for a single conversation: rendered transcript, summary, trust assessment with per-dimension scores and recommendations, structured-output fields, voice-message snippet URLs, duration, and timestamps. Behavior: - Read-only. - Errors when the conversatio...2 params

Returns the full record for a single conversation: rendered transcript, summary, trust assessment with per-dimension scores and recommendations, structured-output fields, voice-message snippet URLs, duration, and timestamps. Behavior: - Read-only. - Errors when the conversatio...

Parameters* required
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
conversation_idstring
Conversation ID (from perspective_list_conversations)
perspective_get_conversationsReturns a token-efficient batch of conversations for bulk analysis. Default output is summaries only (id, summary, trust_score, status, created_at) plus the perspective outline; opt in to full XML transcripts via include_transcripts=true. Default format is TOON (compact); JSON...10 params

Returns a token-efficient batch of conversations for bulk analysis. Default output is summaries only (id, summary, trust_score, status, created_at) plus the perspective outline; opt in to full XML transcripts via include_transcripts=true. Default format is TOON (compact); JSON...

Parameters* required
limitnumber
Number of conversations per batch (max 50)default: 10
cursorstring
Pagination cursor from previous response
formatstring
Output format: toon (default, token-efficient) or jsonone of toon · jsondefault: toon
periodstring
Time period filterone of 7d · 30d · 90d · alldefault: 30d
statusstring
Filter by conversation statusone of completed · partial · abandoned · in_progress
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (from perspective_list or perspective_create)
trust_score_maxnumber
Maximum trust score (0-100)
trust_score_minnumber
Minimum trust score (0-100)
include_transcriptsboolean
Include full conversation transcripts. Default false (summaries only) to reduce tokens. Set true only when you need message-level details.default: false
perspective_createCreates a new perspective in DRAFT status from a natural-language description and starts the design agent. Returns immediately with a job_id and status "pending"; long-poll perspective_await_job with that job_id to receive the generated outline or follow-up question. Behavior:...3 params

Creates a new perspective in DRAFT status from a natural-language description and starts the design agent. Returns immediately with a job_id and status "pending"; long-poll perspective_await_job with that job_id to receive the generated outline or follow-up question. Behavior:...

Parameters* required
descriptionstring
Natural language description of research goals
workspace_idstring
Optional: workspace to create in. If not provided, uses the user's default workspace.
agent_contextstring
Agent behavior mode: 'research' (deep exploratory conversations, default), 'form' (service-oriented with routing), 'survey' (structured with minimal deviation), 'advocate' (listen, then respond with a position/playbook)one of research · form · survey · advocate
perspective_respondSends the user's answer to a follow-up question raised by the design agent during perspective creation, then re-runs the design step. Returns a new pending job_id; long-poll perspective_await_job for the next terminal state. Behavior: - Appends the user's reply to the design c...3 params

Sends the user's answer to a follow-up question raised by the design agent during perspective creation, then re-runs the design step. Returns a new pending job_id; long-poll perspective_await_job for the next terminal state. Behavior: - Appends the user's reply to the design c...

Parameters* required
responsestring
User's response to the follow-up question
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (from perspective_create with status 'needs_input')
perspective_updateApplies natural-language feedback to an existing perspective's outline (e.g., "make it shorter", "add a budget question", "warmer tone"). Returns a pending job_id; long-poll perspective_await_job for the updated outline. Behavior: - Each call kicks off another design pass and...3 params

Applies natural-language feedback to an existing perspective's outline (e.g., "make it shorter", "add a budget question", "warmer tone"). Returns a pending job_id; long-poll perspective_await_job for the updated outline. Behavior: - Each call kicks off another design pass and...

Parameters* required
feedbackstring
Natural language feedback: 'make it shorter', 'add budget question', etc.
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID (must have outline - status OUTLINE_DEFINED or later)
perspective_await_jobLong-polls a perspective-design job (started by perspective_create, perspective_respond, or perspective_update) and returns either its terminal result or another "pending" envelope to keep polling. Behavior: - Read-only — observes a running design job. Safe to call repeatedly....3 params

Long-polls a perspective-design job (started by perspective_create, perspective_respond, or perspective_update) and returns either its terminal result or another "pending" envelope to keep polling. Behavior: - Read-only — observes a running design job. Safe to call repeatedly....

Parameters* required
job_idstring
Job ID returned by create/respond/update
wait_msinteger
Long-poll duration in milliseconds (default 30000, max 45000)
progress_cursorinteger
Resume the progress stream at this chunk index. Use the value returned in the previous pending response to avoid duplicate progress notifications.
automation_listLists every automation configured on a perspective with its trigger, channel (sensitive details redacted), execution mode, enabled state, schedule description, and recent error/success metadata. Behavior: - Read-only. - Errors when the perspective is not found or you do not ha...2 params

Lists every automation configured on a perspective with its trigger, channel (sensitive details redacted), execution mode, enabled state, schedule description, and recent error/success metadata. Behavior: - Read-only. - Errors when the perspective is not found or you do not ha...

Parameters* required
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID
automation_createCreates an automation on a perspective. Triggers: per_interview (fires on every completed conversation) or scheduled (daily/weekly digest). Channels: webhook, email, slack, hubspot. Execution modes: direct (fast, deterministic) or agent (LLM-powered). Behavior: - Each call cre...3 params

Creates an automation on a perspective. Triggers: per_interview (fires on every completed conversation) or scheduled (daily/weekly digest). Channels: webhook, email, slack, hubspot. Execution modes: direct (fast, deterministic) or agent (LLM-powered). Behavior: - Each call cre...

Parameters* required
automationobject
Automation to create
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
perspective_idstring
Perspective ID
automation_updateUpdates fields on an existing automation. Pass a partial updates object with only the fields you want to change; omitted fields are preserved. Toggling enabled or changing schedule/channel/condition takes effect on the next scheduled run. Behavior: - Saves the change to the sa...4 params

Updates fields on an existing automation. Pass a partial updates object with only the fields you want to change; omitted fields are preserved. Toggling enabled or changing schedule/channel/condition takes effect on the next scheduled run. Behavior: - Saves the change to the sa...

Parameters* required
updatesobject
Partial fields to update (pass `enabled` to toggle)
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
automation_idstring
Automation ID
perspective_idstring
Perspective ID
automation_deletePermanently deletes an automation. Pauses any scheduled sends first, then removes the automation. Behavior: - DESTRUCTIVE and irreversible — the automation cannot be recovered. No undo. Confirm with the user before calling. - Errors when the perspective or automation is not fo...3 params

Permanently deletes an automation. Pauses any scheduled sends first, then removes the automation. Behavior: - DESTRUCTIVE and irreversible — the automation cannot be recovered. No undo. Confirm with the user before calling. - Errors when the perspective or automation is not fo...

Parameters* required
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
automation_idstring
Automation ID
perspective_idstring
Perspective ID
automation_testRuns a single end-to-end execution of an existing automation against a mock conversation, returning success/failure plus the channel target and duration. Mirrors a real production firing. Behavior: - Sends REAL messages by default: posts the configured webhook, sends the confi...6 params

Runs a single end-to-end execution of an existing automation against a mock conversation, returning success/failure plus the channel target and duration. Mirrors a real production firing. Behavior: - Sends REAL messages by default: posts the configured webhook, sends the confi...

Parameters* required
test_dataobject
Mock interview data for the test run
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
automation_idstring
Automation ID
override_emailstring
Override the configured recipient (email channel only)
perspective_idstring
Perspective ID
override_webhookstring
Override the configured webhook URL (webhook channel only)
integration_manageRead-only inspector for workspace integrations. Operations: "list" enumerates the registered providers (currently slackbot, hubspot, gmail) and connection status; "connect" returns a setup URL the user opens in a browser to complete OAuth; "search_tools" returns the available...4 params

Read-only inspector for workspace integrations. Operations: "list" enumerates the registered providers (currently slackbot, hubspot, gmail) and connection status; "connect" returns a setup URL the user opens in a browser to complete OAuth; "search_tools" returns the available...

Parameters* required
querystring
Search query (required for 'search_tools')
providerstring
Provider (required for connect/search_tools)one of slackbot · hubspot · gmail
operationstring
The operation to performone of list · connect · search_tools
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
participant_inviteCreates participant invites for a perspective and returns 48-hour magic-link URLs, optionally sending invitation emails. Pass EITHER participants (creates new invites) OR invite_ids (reuses existing invites, minting a fresh 48h link) — never both. Behavior: - With participants...7 params

Creates participant invites for a perspective and returns 48-hour magic-link URLs, optionally sending invitation emails. Pass EITHER participants (creates new invites) OR invite_ids (reuses existing invites, minting a fresh 48h link) — never both. Behavior: - With participants...

Parameters* required
invite_idsarray
Invite IDs from a previous call. Reuses existing invite records. Mutually exclusive with participants.
send_emailboolean
When true, sends invitation emails. When false (default), only returns invite URLs.default: false
participantsarray
Participants to create new invites for. Mutually exclusive with invite_ids.
workspace_idstring
Workspace ID (from workspace_get_default or workspace_list) or workspace slug (uniqueName)
custom_messagestring
Custom message body in the email. Only used when send_email is true.
custom_subjectstring
Custom email subject line. Only used when send_email is true.
perspective_idstring
Perspective ID (from perspective_list or perspective_create)

Perspective AI

Perspective AI MCP Server

Forms are costing you business. An AI concierge turns them into conversations.

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.

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.

What this MCP server does

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.

See Use cases for the full workflow and Available tools for the tool surface.

Connect via OAuth (recommended)

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 under Settings → Connected Apps in your workspace, and you can revoke access anytime.

The MCP URL is the same for everyone:

https://getperspective.ai/mcp

Claude Code

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

Cursor and VS Code

Add to your mcp.json:

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

Claude.ai (web and desktop)

Open the Add custom connector modal and fill:

FieldValue
NamePerspective AI
Remote MCP server URLhttps://getperspective.ai/mcp

Click Add, then complete the OAuth browser flow. (Manual path: Customize → Connectors → Add custom connector. See Anthropic's guide. Available on Free, Pro, Max, Team, and Enterprise plans.)

Other MCP clients

Stdio-only clients can use mcp-remote, which discovers OAuth metadata automatically:

{
  "mcpServers": {
    "perspective": {
      "command": "npx",
      "args": ["mcp-remote", "https://getperspective.ai/mcp"]
    }
  }
}

The first time you call a Perspective tool, your client opens a browser window to complete OAuth. Subsequent requests reuse the token.

Connect with a personal access token

If your client doesn't support OAuth or you'd rather authenticate with a long-lived token, generate one at Perspective AI Settings → MCP.

Generate an MCP access token

Claude Desktop one-click install

  1. Download perspective.mcpb
  2. Double-click to open in Claude Desktop
  3. Click Install, then paste your token when prompted

Claude Code

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

Cursor and VS Code

Add to your mcp.json:

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

Other MCP clients

For stdio-only clients, use mcp-remote with an explicit Authorization header:

{
  "mcpServers": {
    "perspective": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://getperspective.ai/mcp",
        "--header",
        "Authorization: Bearer YOUR_TOKEN"
      ]
    }
  }
}

See the full MCP documentation for troubleshooting and advanced setup.

Available tools

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

Workspaces

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

Design & iterate

  • 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

Deploy & distribute

  • 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

Analyze

  • 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

Automate

  • 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

Use cases

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:

    • Interviewer: Scales deep, qualitative interviews without losing quality
    • Concierge: Replaces static forms with delightful conversational flow
    • Evaluator: Turns boring surveys into engaging conversations
    • Advocate: Listens first, then responds on behalf of a position, brand, or cause

    Browse 180+ templates or use cases by role and industry for inspiration. Example prompts:

    • "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."

Security & data

  • OAuth: Tokens issued via OAuth are scoped to the workspace and tied to the connected client. Revoke anytime under Settings → Connected Apps.
  • Personal access tokens: PATs are tied to your Perspective AI account and authorize the server to act on your behalf within your workspaces. Generate, rotate, or revoke at getperspective.ai/settings/mcp.
  • Transport: All traffic is TLS-encrypted. Tokens are sent only in the Authorization header to https://getperspective.ai/mcp.
  • Data residency: Conversation data stays inside your Perspective AI workspace. The .mcpb bundle is a thin stdio-to-HTTP proxy; it does not store or cache responses locally.

Building from Source

npm install
npm run pack

Outputs perspective.mcpb in the current directory.

Releasing

npm run release

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

Links

  • Get Access Token
  • Full MCP Documentation
  • Brand Assets
  • Support

Badges

Smithery badge Glama MCP server

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Registryactive
TransportHTTP
UpdatedApr 28, 2026
View on GitHub