# Usercall Mcp

> MCP server that lets AI agents run real user interviews and retrieve themes and quotes.

- **Type:** MCP server
- **Install:** `agentstack add mcp-junetic-usercall-mcp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [junetic](https://agentstack.voostack.com/s/junetic)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [junetic](https://github.com/junetic)
- **Source:** https://github.com/junetic/usercall-mcp
- **Website:** https://usercall.co

## Install

```sh
agentstack add mcp-junetic-usercall-mcp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Usercall MCP - AI agents that run real user interviews

[](https://www.npmjs.com/package/@usercall/mcp)
[](LICENSE)

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

Usercall MCP lets AI agents run user interviews via voice calls and return structured insights with themes and verbatim quotes.

Works with Claude Desktop, Cursor, and any MCP-compatible client.

## 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.

---

## Example workflow

```
Agent: "Why are users confused about onboarding?"

→ create_study
→ share interview_link with users
→ get_study_results
```

The returned `interview_link` can be shared with participants through email, Slack, Discord, or [in-product prompts](https://www.usercall.co/research-triggers).

Example result:

```json
{
  "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

↓

Usercall Agent API

↓

Real user interviews

↓

Themes and verbatim quotes returned to the agent

---

## Try it in 60 seconds

### 1. Get an API key

Sign in at [app.usercall.co](https://app.usercall.co) → **Home → Developer → Create API key**

### 2. Add to your MCP client

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

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

**Cursor** (`.cursor/mcp.json`):

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

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

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 themes and verbatim quotes

---

## 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
language: "en"

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

---

## Tools

### `create_study`

Creates an interview study and returns an `interview_link` to share with participants.

| Field                       | Type               | Required |
| --------------------------- | ------------------ | -------- |
| `key_research_goal`         | string             | yes      |
| `business_context`          | string             | yes      |
| `additional_context_prompt` | string             | no       |
| `target_interviews`         | number             | no       |
| `language`                  | `auto \| en \| ko` | no       |
| `duration_minutes`          | number             | no       |
| `metadata`                  | object             | no       |
| `study_media`               | object             | no       |

**study_media** (optional) — visual stimulus shown during all interview questions:

| Field         | Type                   | Required |
| ------------- | ---------------------- | -------- |
| `type`        | `image \| prototype`   | yes      |
| `url`         | string (URL)           | yes      |
| `description` | string (max 500 chars) | no       |

- `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`

Updates an existing study. Use this to increase interview slots, add/update media, or disable the link.

| Field               | Type        | Required |
| ------------------- | ----------- | -------- |
| `study_id`          | uuid string | yes      |
| `target_interviews` | number      | no       |
| `is_link_disabled`  | boolean     | no       |
| `study_media`       | object      | no       |

The `study_media` object follows the same schema as in `create_study`.

### `get_study_status`

Returns the current lifecycle status of a study.

| Field      | Type        |
| ---------- | ----------- |
| `study_id` | uuid string |

Status values: `running` · `analyzing` · `complete`

Response includes interview progress fields, including
`completed_interviews` and `target_interviews`.

### `get_study_results`

Returns analysis output once the study is complete.

| Field      | Type              | Required |
| ---------- | ----------------- | -------- |
| `study_id` | uuid string       | yes      |
| `format`   | `summary \| full` | no       |

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

### `delete_study`

Permanently deletes a study and all associated data (recordings, transcripts). Releases unused reserved credits.

| Field      | Type        | Required |
| ---------- | ----------- | -------- |
| `study_id` | uuid string | yes      |

---

## Example workflow

```
1. create_study
   key_research_goal: "Why do users drop off during onboarding?"
   business_context: "B2B SaaS, 3-step signup flow"

   → returns { study_id, interview_link }

2. Share interview_link with participants
   (email, Slack, in-product prompt, etc.)

3. get_study_status
   → "analyzing"

4. get_study_results
   → themes + verbatim quotes returned to the agent
```

### 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. Share interview_link — participants see the mockup during interview
```

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

---

## Requirements

- Node.js 18+
- A valid Usercall API key

---

## Self-hosting / development

```bash
pnpm install
pnpm build
USERCALL_API_KEY="your_key_here" pnpm start
```

Smoke test:

```bash
USERCALL_API_KEY="your_key_here" pnpm smoke
```

---

## Troubleshooting

| Error                      | Fix                                        |
| -------------------------- | ------------------------------------------ |
| `Missing USERCALL_API_KEY` | Set the env var before starting            |
| `401 Unauthorized`         | Invalid or revoked API key                 |
| `402 Insufficient credits` | Add credits at app.usercall.co             |
| `500` on create            | Verify your key has access to Agent API v1 |

---

## License

MIT

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [junetic](https://github.com/junetic)
- **Source:** [junetic/usercall-mcp](https://github.com/junetic/usercall-mcp)
- **License:** MIT
- **Homepage:** https://usercall.co

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-junetic-usercall-mcp
- Seller: https://agentstack.voostack.com/s/junetic
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.