In addition to the REST API, Share of Model exposes a Model Context Protocol, MCP, server that allows AI assistants such as Claude Desktop, Claude Code, MCP Inspector, or custom agents to call Share of Model endpoints directly as tools.
Any MCP-compatible client can interact with Share of Model without requiring a custom integration. Simply connect using your existing Share of Model account and start querying your data in natural language.
Connect from Claude Desktop
Open Settings, then Connectors, scroll to the bottom, and click Add custom connector.
Paste the following URL then click Connect:
https://mcp.shareofmodel.ai/mcp
A browser window will open so you can sign in with your Share of Model account, using the same credentials as the web app. Once authenticated, the assistant will have access to the available tools.
Connect from Claude Code
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 so you can complete the authentication flow.
Connect from MCP Inspector
npx @modelcontextprotocol/inspector
In the Inspector UI, select Streamable HTTP as the transport, paste the MCP URL, then click Connect:
https://mcp.shareofmodel.ai/mcp
On first connection, you will be prompted to sign in with your Share of Model account.
Available tools
Only endpoints tagged mcp in the OpenAPI specification are exposed as MCP tools.
To keep interactions safe and predictable, only read-only endpoints, GET routes, are currently available through MCP. This makes it easy to explore analyses, inspect brand perception data, review asset evaluations, and generate strategic insights directly from an MCP client.
Example prompts
Once connected, users can ask assistants questions such as:
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?
Notes
All exposed MCP tools are read-only, which means assistants can safely explore available analyses, retrieve metrics, review evaluations, and generate insights without modifying workspace data.
For more information about the protocol itself, see the Model Context Protocol specification.