'%3e%3cpath%20fill-rule='evenodd'%20clip-rule='evenodd'%20d='M0%2062.3176C0%2027.9001%2027.8995%200.00181961%2062.3134%200.00181961L62.3999%2062.2311C62.3999%2096.6462%2034.5004%20124.544%200.0852901%20124.544'%20fill='%233A3D3C'/%3e%3c/g%3e%3cpath%20d='M62.3994%2062.2461V0C96.8133%200%20124.713%2027.8982%20124.713%2062.3158'%20fill='url(%23paint0_linear_6331_3458)'/%3e%3cpath%20fill-rule='evenodd'%20clip-rule='evenodd'%20d='M45.617%2026.2827C47.7276%2026.2827%2049.4382%2027.9933%2049.4382%2030.1052C49.4382%2032.2146%2047.7276%2033.9252%2045.617%2033.9252C43.5064%2033.9252%2041.7958%2032.2146%2041.7958%2030.1052C41.7958%2027.9933%2043.5064%2026.2827%2045.617%2026.2827Z'%20fill='%23F9F6EF'/%3e%3cpath%20fill-rule='evenodd'%20clip-rule='evenodd'%20d='M45.6168%2045.2338C37.2596%2045.2338%2030.4857%2038.461%2030.4857%2030.1038C30.4857%2021.7454%2037.2596%2014.9702%2045.6168%2014.9702C53.9753%2014.9702%2060.7492%2021.7454%2060.7492%2030.1038C60.7492%2038.461%2053.9753%2045.2338%2045.6168%2045.2338ZM45.6168%2012.6686C35.9875%2012.6686%2028.1816%2020.4744%2028.1816%2030.1038C28.1816%2039.7308%2035.9875%2047.5378%2045.6168%2047.5378C55.245%2047.5378%2063.0508%2039.7308%2063.0508%2030.1038C63.0508%2020.4744%2055.245%2012.6686%2045.6168%2012.6686Z'%20fill='%23FECE01'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_6331_3458'%20x1='62.2719'%20y1='4.01754'%20x2='108.703'%20y2='70.5262'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%239ED5CB'/%3e%3cstop%20offset='1'%20stop-color='%23FCE18E'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
Which MCP do I need?
Toucan AI offers two MCP servers: the Maker MCP to build with your AI agent, and the Explorer MCP to let your users ask questions from their own chat.
The Model Context Protocol (MCP) lets an AI assistant use another product's tools. Toucan AI offers two MCP servers, for two different jobs. Both are available with the Grow plan.
| Maker MCP | Explorer MCP | |
|---|---|---|
| In one line | Build from your agent. | Ask from your product. |
| Who uses it | A maker or admin, in Claude, Cursor, VS Code or another agent. | The end users of your product, through a chat you already have. |
| What it does | Models your data, secures it and builds data apps. | Answers a data question with text and charts. |
| How it signs in | You approve a connection in your browser (OAuth). | Your backend mints a one-hour embed token per user. |
| What the data is scoped to | Your permissions, and any user you preview as. | The attributes in the token, with row-level security applied. |
| Start here | Build with an AI agent | Integrate Toucan into your own AI chat |
Which one is for me?
- I want to build an analytics experience, faster, from my AI agent. Use the Maker MCP.
- My product already has a chat, and I want it to answer data questions. Use the Explorer MCP.
- I want my users to ask questions from Claude or ChatGPT directly. Not available yet: the Explorer MCP needs a token your backend creates, so it cannot be added to a generic client in one click. See its limits.
- I want Toucan's team to build it for me. See Crew.
Both share your governance
Neither server opens a back door. Both read your data through the same definitions and the same access rules: what the Maker MCP builds and what the Explorer MCP answers are scoped by your row-level and column-level security. For details, see MCP access and security, and for every tool, the MCP tools reference.