> ## Documentation Index
> Fetch the complete documentation index at: https://docs.shareofmodel.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server Setup

> Connect Claude Desktop, Claude Code, MCP Inspector or any MCP client to Share Of Model.

In addition to the REST API, Share Of Model exposes a **Model Context Protocol (MCP)** server. Any MCP-compatible client — Claude Desktop, Claude Code, MCP Inspector, custom agents — can call Share Of Model endpoints directly as tools.

There is no custom integration to build: connect with your existing Share Of Model account and start querying your data in natural language.

## Connect your client

<Tabs>
  <Tab title="Claude Desktop">
    <Steps>
      <Step title="Open the connector settings">
        Open **Settings → Connectors**, scroll to the bottom, and click **Add custom connector**.
      </Step>

      <Step title="Paste the MCP URL">
        ```
        https://mcp.shareofmodel.ai/mcp
        ```

        Click **Connect**.
      </Step>

      <Step title="Sign in">
        A browser window opens — sign in with your Share Of Model account (same credentials as the web app). Once authenticated, the assistant has access to the available tools.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude Code">
    Run the following command:

    ```bash theme={null}
    claude mcp add --transport http share-of-model https://mcp.shareofmodel.ai/mcp
    ```

    The first time you call a tool, Claude Code opens your browser to complete authentication.
  </Tab>

  <Tab title="MCP Inspector">
    Launch the inspector:

    ```bash theme={null}
    npx @modelcontextprotocol/inspector
    ```

    In the UI, select **Streamable HTTP** as the transport, paste the MCP URL, and click **Connect**:

    ```
    https://mcp.shareofmodel.ai/mcp
    ```

    On first connection, sign in with your Share Of Model account.
  </Tab>
</Tabs>

## Available tools

Only endpoints tagged `mcp` in the OpenAPI specification are exposed as MCP tools. Both API surfaces are covered — the Core API (organisations and workspaces, analyses, brand metrics, asset evaluations) and the Search API (visibility score, presence rate, keyword gaps) — plus `get_current_user`, which lets the assistant tailor answers to you.

<Note>
  To keep interactions safe and predictable, only **read-only `GET` endpoints** are currently exposed via MCP. You can explore analyses, inspect brand-perception data, review asset evaluations, and generate strategic insights — without modifying workspace data.
</Note>

The server also ships **domain skills** — glossaries, reporting playbooks, security and compliance notes — that the assistant loads on its own. In practice this means you can ask about a metric by name without first explaining what it measures. The documentation search tools are mounted too, so the assistant can look things up in these docs mid-conversation.

## Guided workflows

Ten pre-built prompts cover the most common analyses, so you don't have to phrase the request yourself:

| Prompt                         | What it produces                            |
| ------------------------------ | ------------------------------------------- |
| `brand_visibility_brief`       | Executive brief on a brand's AI visibility. |
| `compare_brands`               | Head-to-head brand comparison.              |
| `weekly_brand_update`          | Week-over-week metrics summary.             |
| `competitive_landscape`        | Top brands in a category.                   |
| `persona_breakdown`            | Performance by target persona.              |
| `attribute_deep_dive`          | Deep analysis of a single attribute.        |
| `search_visibility_scorecard`  | Search visibility scorecard.                |
| `visibility_gap_vs_competitor` | Search query gaps versus a competitor.      |
| `asset_effectiveness_report`   | Creative asset evaluation summary.          |
| `geo_opportunities`            | Cross-module GEO recommendations.           |

In Claude Desktop and Claude Code these appear in the prompt or slash-command picker once the connector is authenticated.

## Example prompts

Once connected, ask your assistant questions like:

* *List the workspaces I have access to.*
* *Show me all completed analyses in this workspace.*
* *What brands are included in the running shoes analysis?*
* *Compare the share of voice between Nike and Adidas over the last 30 days.*
* *Which brands have the strongest awareness index?*
* *Show me the key strengths and weaknesses for each competitor.*
* *How does our brand perform across ChatGPT, Gemini, and Claude?*
* *Give me strategic insights for this analysis.*
* *What assets have been evaluated and which ones scored highest?*

## What's next

<CardGroup cols={2}>
  <Card title="API Documentation Guide" icon="code" href="/platform/getting-started/api-documentation-user-guide">
    Use the REST API directly.
  </Card>

  <Card title="API Reference" icon="book" href="/api-reference/mcp-integration">
    Browse the MCP integration spec.
  </Card>
</CardGroup>