Usercall MCP - AI agents that run real user interviews

AI can build products. But it still doesn't talk to users.

Give your AI agents the ability to ask real users why.

Usercall MCP runs AI-moderated voice or text interviews with real users. Use it to learn why users churn, where onboarding drops off, or why an action failed, and get themes, insights, and verbatim quotes.

Why this exists

AI agents can now build and ship products extremely quickly.

But most agents still rely on synthetic feedback or assumptions about users.

Usercall MCP lets agents gather real qualitative feedback directly from users.

Related MCP server: gq-insight-mcp

Choose a connection

Recommended: hosted MCP (Claude, ChatGPT, Cursor, Grok Bot)

Add https://mcp.usercall.co as a remote MCP connector / custom connector.

• OAuth sign-in (no API key, no npx)

• Same tools as this package (studies + Research Triggers)

• Docs: app.usercall.co/docs/mcp

• Cursor Directory / Grok Bot: this repo ships .mcp.json so cursor.directory can install the hosted connector. Grok Bot cannot run the local npx package.

ChatGPT plugin package

Root plugin.json, mcp.json, and skills/ are the ChatGPT submission package (version in plugin.json, not package.json). Validate it and write the ZIP with:

pnpm plugin:check

The ZIP is dist/usercall-chatgpt-plugin-<version>.zip. Do not upload it unless someone asks to submit.

Install in Cursor

Community. Already listed at cursor.directory/plugins/usercall.

Official Marketplace. Once the listing is live, install from the Cursor Marketplace. Submit the repo at cursor.com/marketplace/publish.

Manual. Add the hosted MCP. OAuth sign-in, no API key.

{
  "mcpServers": {
    "usercall": {
      "url": "https://mcp.usercall.co"
    }
  }
}

This package: local / API-key / machine-to-machine

Use @usercall/mcp over stdio when you want a Bearer API key (scripts, local clients, M2M).

1. Sign in at app.usercall.co → Home → Developer → Create API key

2. Run npx -y @usercall/mcp with USERCALL_API_KEY

Example workflow

Agent: "Why are users confused about onboarding?"

→ create_study
→ share interview_link with users
→ get_study_results

The returned interview_link is an https://app.usercall.co/interview/ URL. Share it with participants through email, Slack, Discord, or in-product prompts.

Example result:

{
  "themes": [
    {
      "name": "Onboarding confusion",
      "summary": "Users struggled to understand the second step.",
      "quotes": [
        "I wasn't sure what the app was asking me to do.",
        "I didn't know I had to verify my email before continuing."
      ]
    },
    {
      "name": "Pricing confusion",
      "summary": "Free plan limits were not clearly communicated.",
      "quotes": ["I wasn't sure if the free plan included analytics."]
    }
  ]
}

How it works

AI Agent

↓

Usercall MCP (hosted OAuth or this stdio package)

↓

Usercall Agent API

↓

Real user interviews

↓

Themes and verbatim quotes returned to the agent

With Research Triggers, the agent can also target users in your product:

Analytics MCP (PostHog, Mixpanel, …) finds a behavior

↓

Usercall MCP creates a study and a paused Research Trigger

↓

You activate it in Usercall

↓

The Usercall SDK invites matching users to an interview right after the behavior

Research Triggers

Analytics tells an agent what users do. Research Triggers let it ask them why.

User:  "Look at our PostHog data and find something worth investigating."

Agent (PostHog MCP):  users who test a study rarely launch one.

Agent (Usercall MCP):
  list_trigger_events()                  → study_tested, study_launched, …
  get_trigger_event_schema("study_tested")
                                         → properties: source, interview_type
                                           traits: plan ("free", "pro"), account_type
  create_study(...)  or  list_studies()
  create_research_trigger({
    study_id, event_name: "study_tested",
    traits: { plan: "free" }, sampling_percent: 25, max_invites_per_day: 10
  })                                     → status: "paused", summary, activation_url

Agent: "I've prepared a Research Trigger. When: study_tested · Audience: plan = free ·
        25% sampled · max 10 invites/day. It's paused. A human activates it here: <activation_url>"

• The Usercall SDK has to be installed. If list_trigger_events returns nothing, call get_trigger_sdk_setup (with your analytics provider and event names) to get the snippet. Coding agents can install it for you.

• Only events Usercall has actually received can be used. Filters are exact matches on event properties or user traits. get_trigger_event_schema shows which field is which.

• Unsupported conditions are rejected, not silently dropped. These include event counts, sequences, absence ("did not do X"), time windows, and not-equals. get_trigger_capabilities returns the full list.

Local install (API key)

1. Get an API key

Sign in at app.usercall.co → Home → Developer → Create API key

2. Add to your MCP client

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

{
  "mcpServers": {
    "usercall": {
      "command": "npx",
      "args": ["-y", "@usercall/mcp"],
      "env": {
        "USERCALL_API_KEY": "your_key_here"
      }
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "usercall": {
      "command": "npx",
      "args": ["-y", "@usercall/mcp"],
      "env": {
        "USERCALL_API_KEY": "your_key_here"
      }
    }
  }
}

For Claude, ChatGPT, or Cursor remote connectors, prefer https://mcp.usercall.co instead of this JSON config.

Restart your MCP client.

3. Ask your agent

Run user interviews to understand why users drop off during onboarding.

Context:
- B2B SaaS product
- 3-step signup flow

Goal:
Identify confusion points and friction.

Target interviews: 5
Language: ko
Interview mode: voice

Show participants this prototype during the interview:
https://www.figma.com/proto/abcd1234/onboarding-flow

The agent will:

1. create a study

2. return an interview link

3. collect responses

4. return the summary (themes, insights, and risks)

Structured tool example

Equivalent create_study tool call:

create_study
key_research_goal: "Understand why users drop off during onboarding"
business_context: "B2B SaaS signup flow"
target_interviews: 5
languages: ["en"]
interview_mode: "voice"

study_media:
  type: "prototype"
  url: "https://www.figma.com/proto/abcd1234/onboarding-flow"
  description: "New onboarding flow concept"

Tools

create_study

Create an AI-moderated interview study to learn why users churn, drop off in onboarding, fail an action, or where a product assumption is wrong. Returns HTTP 201 with study_id and interview_link for a voice, text, or voice-and-text interview. interview_link is an https://app.usercall.co/interview/ URL. key_research_goal is required and cannot be changed later. business_context is optional. Defaults: target_interviews 1, duration_minutes 12, interview_mode voice. One active agent study per account. Does not run the interview or invite a participant. HTTP 402 includes checkout_url.

One locale turns the language picker off; two or more turn it on. Research goal cannot be changed after create.

study_media (optional). Visual stimulus shown during all interview questions:

• image: Direct image URL (.png, .jpg, .gif, .webp)

• prototype: Figma prototype URL (converted to interactive embed)

• Media is only visible to web participants; phone callers won't see it

update_study

Update an interview study: slots, guide questions, intro, languages, voice, or an image or Figma prototype shown to participants. Returns the updated study. key_research_goal cannot be changed. is_link_disabled true stops new interviews and keeps recordings. One locale hides the language picker; two or more show it. Query parameters on interview_link are ignored until enable_link_context is true. study_media null clears media. API errors include http_status. Does not dry-run the guide or invite a participant.

Pass study_media: null to clear media. The study_media object follows the same schema as in create_study.

get_study_status

Check whether interviews about churn, onboarding, or a failed action have started. Returns completed_interviews, target_interviews, interview_link, and next_step. interview_link is an https://app.usercall.co/interview/ URL. Zero interviews is status: "not_started". running means an interview is underway. running and analyzing include no findings, themes, or quotes. next_step is update_study while a ready review still has unapplied edits. After the guide matches those edits, or when there are no edits, share is correct if a terminal simulation or review exists and completed interviews are still 0. Does not change the study.

Status values: not_started · running · analyzing · complete

get_study_results

Get interview findings after real users have talked: themes, insights, risks, and verbatim quotes. format omitted or summary returns themes, insights, and risks. format=full also returns transcripts. Empty themes mean analysis is not ready. Does not create interviews or edit the guide.

Summary/full responses include study progress fields and analysis output.

simulate_interview

Dry-run an interview guide before a real participant joins, including a question about churn, onboarding, or a failed action. Omit simulation_id to start; returns immediately with status: "running" and a simulation_id. Pass simulation_id to read that run. Omit persona and the server writes one from the research question, including that the person did not do the thing the study is about. A sent persona is used as-is: name is 1–80 characters and prompt is 1–4000. Result status is pass, fail, or error. A finished transcript is [{ "role": "agent" | "user", "content": "..." }]. Do not expect call_id, timezone, or timestamps. Max 5 simulations per account per UTC day. HTTP 429 means the daily cap is reached. A dry-run does not change completed_interviews and does not invite a participant.

Omit simulation_id to POST /api/v1/agent/studies/{studyId}/simulations. Pass simulation_id to GET that simulation. The tool does not poll. Omit persona on start and the server writes one. A sent persona is forwarded unchanged.

review_study

Review an interview guide before real users see the questions, including a question about churn, onboarding, or a failed action. The body keeps findings and adds suggested_edits. suggested_edits is an update_study body, or null when there is nothing to change. Send suggested_edits to update_study as-is. Nothing is applied for you. Costs 1 credit. Request is study_id only; call_ids are not accepted. Works when the in-app review control is hidden. HTTP 402 includes checkout_url. Reads the guide only: no transcripts.

Sends study_id only. It does not send call_ids. A non-null suggested_edits value is the update_study body, unchanged.

delete_study

Permanently delete an interview study, its recordings, and unused reserved credits. Cannot be undone. Does not delete in-product research triggers.

Research Trigger tools

create_research_trigger

For page-visit triggers, use source: "page_visit" and event_name: "$pageview", with url and optionally dwell_seconds.

Delivery.

• intercept (default) shows the Usercall widget in your product, and the user takes a voice or text interview in the page. The modes come from the study; list_studies returns each study's interview_mode.

• webhook POSTs each matched user to webhook_url, with their user ID, email if known, traits, event properties and a personal interview link. If webhook_secret is set, requests carry an x-usercall-signature HMAC header.

• Only public https URLs are accepted, and the activation page shows the destination before a person activates the trigger.

Safety

• Agents cannot activate triggers. Triggers are always created paused. Calling update_research_trigger with status: "active" returns HTTP 409 and the activation_url. A person has to open that link, review who will be invited, what they will see and the credit cost, and click Activate.

• Changes to an active trigger need re-approval. Changing an active trigger's configuration pauses it again.

• Secret keys are never returned. The ingestion secret key never comes back from any tool.

Example workflow

1. create_study
   key_research_goal: "Why do users drop off during onboarding?"
   business_context: "B2B SaaS, 3-step signup flow"
   target_interviews: 5
   languages: ["ko"]
   interview_mode: "voice"

   → HTTP 201 { study_id, interview_link: "https://app.usercall.co/interview/..." }
   (`business_context` is optional; `key_research_goal` alone still creates a study)

2. simulate_interview
   study_id
   → status "running", simulation_id
   call again with simulation_id
   → pass, fail, or error
   finished transcript: [{ "role": "agent" | "user", "content": "..." }]
   omit persona unless you want a specific one (name 1–80, prompt 1–4000)

3. review_study
   study_id
   → findings, plus suggested_edits (an update_study body, or null)
   send suggested_edits to update_study as-is; nothing is applied for you

4. Share interview_link with participants
   (email, Slack, in-product prompt, etc.)
   share is correct once a terminal simulation or review exists,
   completed interviews are still 0, and any suggested edits are already on the guide

5. get_study_status
   → "not_started" when completed_interviews is 0
   → "running" while an interview is underway
   → next_step "update_study" while a ready review still has unapplied edits

6. get_study_results
   → summary: themes, insights, and risks
   use format=full only for a quote

With visual stimulus

1. create_study
   key_research_goal: "Get feedback on new dashboard design"
   business_context: "Redesigning analytics dashboard for power users"
   study_media:
     type: "image"
     url: "https://example.com/dashboard-mockup.png"
     description: "New dashboard design concept"

   → returns { study_id, interview_link }

2. After simulate_interview passes, a human shares interview_link. Participants see the mockup during the interview.

For Figma prototypes, use type: "prototype" with a Figma proto URL.

Requirements

• Node.js 18+

• A valid Usercall API key (local / API-key path only)

Self-hosting / development

pnpm install
pnpm build
USERCALL_API_KEY="your_key_here" pnpm start

Tests and smoke tests:

pnpm test                                   # unit + MCP contract tests
USERCALL_API_KEY="your_key_here" pnpm smoke # creates a real study
USERCALL_API_KEY="your_key_here" SMOKE_STUDY_ID="<uuid>" SMOKE_EVENT_NAME="<observed event>" pnpm smoke:triggers

Official MCP Registry

Usercall is listed on the Official MCP Registry as co.usercall/mcp.

Troubleshooting

Remote Claude / ChatGPT / Cursor connectors should use https://mcp.usercall.co (OAuth). This package is the API-key stdio path.

License

MIT