> For the complete documentation index, see [llms.txt](https://docs.flora.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flora.ai/mcp/install.md). # Install FLORA MCP Pick your AI client (Claude, Claude Code, ChatGPT, Codex, Cursor, VS Code or another) and connect it to FLORA MCP in about a minute. [FLORA MCP](https://flora.ai/mcp) is a hosted server, so there's nothing to download: you point your client at one URL and sign in with your FLORA account. Find your client below and follow its page. | Setting | Value | | -------------- | ------------------------------------------------------------------------------------------------------------------ | | Server URL | `https://agents.flora.ai/mcp` | | Transport | Streamable HTTP (remote server, nothing to install) | | Sign-in | OAuth with your FLORA account. Headless clients can send a FLORA API key as `Authorization: Bearer ` instead. | | Server name | `flora` | | Check it works | Ask your agent: "List my FLORA workspaces. Don't generate anything." | ## Pick your client | Client | Fastest route | Client plan needed | Guide | | ------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------- | -------------------------------------------------------------- | | Claude (web and Desktop) | **Customize → Connectors → Add custom connector**, paste the URL | Any plan. Free allows one custom connector. On Team and Enterprise, an Owner adds it. | [Claude](/mcp/install/claude.md) | | Claude Code | The FLORA plugin (server and skills), or `claude mcp add --transport http flora https://agents.flora.ai/mcp` | Any Claude Code setup | [Claude Code](/mcp/install/claude-code.md) | | ChatGPT | Open the [FLORA app](https://chatgpt.com/plugins/plugin_asdk_app_6a8c516c7e308191a0091f1b9c98a621) and click **Connect** | A plan and workspace where ChatGPT apps are available. Enterprise and Edu admins turn apps on. | [ChatGPT](/mcp/install/chatgpt.md) | | OpenAI Codex | `codex mcp add flora --url https://agents.flora.ai/mcp` | Any Codex setup | [Codex](/mcp/install/codex.md) | | Cursor | One-click install link, or `~/.cursor/mcp.json` | Any Cursor plan | [Cursor](/mcp/install/cursor.md) | | VS Code | `code --add-mcp '{"name":"flora","type":"http","url":"https://agents.flora.ai/mcp"}'` | GitHub Copilot. Business and Enterprise need the **MCP servers in Copilot** policy on. | [VS Code](/mcp/install/vscode.md) | | Windsurf, Gemini CLI, Copilot Studio, Hermes, OpenClaw | Client-specific config | See each section | [Other clients](/mcp/install/other-clients.md) | | Anything else | URL, Streamable HTTP, OAuth | Remote MCP support, or `mcp-remote` | [Any MCP client](/mcp/install/other-clients.md#any-mcp-client) | **On the FLORA side,** API and MCP are included from Starter up. A Free account can also connect and generate on the $2.50 of usage every new workspace gets. Each generation is billed in US dollars to the workspace you choose. See [How FLORA pricing works](/plans-and-billing/pricing.md) and [Authentication](/mcp/authentication.md#who-can-connect). ## Any MCP client Your client needs three things: the URL `https://agents.flora.ai/mcp`, the Streamable HTTP transport, and OAuth sign-in (or a FLORA API key in the `Authorization` header). If it only runs local servers, bridge with `npx -y mcp-remote https://agents.flora.ai/mcp`. The [Any MCP client](/mcp/install/other-clients.md#any-mcp-client) section has config shapes, the `mcp-remote` setup and a health check. ## Open a project in your agent From any canvas, the **Open in Agent** menu in the canvas toolbar hands the project to an agent with a prompt already filled in. An empty canvas offers the same agents under **Your canvas is empty**, and marks the last one you used. | Agent | Install | Chat with project | | ------------ | ------------------------------------------------------------- | ----------------------------------------------- | | **Claude** | **Install MCP** opens claude.ai's add-custom-connector page | Opens a new chat on claude.ai | | **ChatGPT** | **Install Plugin** opens the FLORA plugin | Opens a new ChatGPT chat | | **Cursor** | **Install MCP** installs FLORA MCP in Cursor in one click | Opens a Cursor chat | | **Grok Bot** | **Install Bot** opens the FLORA bot for Grok on X | Opens Grok Bot with the task filled in | | **Other** | **Install MCP** copies a setup prompt to paste into any agent | Copies a one-line task to paste into your agent | Run **Install** once per agent, then use **Chat with project** whenever you want the agent to work on this canvas. Opening an agent needs a workspace with API and MCP access; otherwise FLORA asks you to upgrade, or to ask a billing admin. ## After you connect 1. Ask your agent: "List my FLORA workspaces. Don't generate anything." If it lists them, you're connected. 2. Follow the [quickstart](/mcp/quickstart.md) to make your first image, with a cost quote first. 3. Add FLORA's [skills](/mcp/skills.md) for bigger jobs such as batches and refine loops. Connection trouble? See [Troubleshooting](/mcp/troubleshooting.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.flora.ai/mcp/install.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.