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

# API Reference

> Programmatic access to Summand via the Model Context Protocol.

Summand exposes its read-side API through a hosted [Model Context Protocol](https://modelcontextprotocol.io) server. Any MCP-aware client — claude.ai, ChatGPT, or your own — can sign in with OAuth and query your datasets, semantic-layer components, and surprise findings without writing a line of glue code.

A traditional REST API is on the roadmap, but MCP is the supported integration surface today.

## The Summand MCP server

* **Endpoint:** `https://mcp.summand.com/mcp`
* **Transport:** streamable-HTTP
* **Auth:** OAuth 2.1
* **Access model:** scoped to whatever the signed-in user can already see in the dashboard — owned datasets plus anything explicitly shared with them

<Columns cols={2}>
  <Card title="MCP server overview" href="/api-reference/mcp/overview">
    What the server is and what it exposes.
  </Card>

  <Card title="Connect a client" href="/api-reference/mcp/connect">
    Wire up claude.ai, ChatGPT, or any OAuth-aware MCP client.
  </Card>

  <Card title="Tools reference" href="/api-reference/mcp/tools">
    Parameters and example prompts for every tool.
  </Card>
</Columns>

## What about a REST API?

A public REST API is on our roadmap and will follow the same authorization model (OpenFGA-backed, per-resource grants and visibility) with bearer-token authentication. Enterprise customers with a concrete use case — backend integrations, scheduled refresh jobs, custom dashboards — can request early access by emailing [enterprise@summand.com](mailto:enterprise@summand.com) with a one-paragraph description of what you'd build.