Server data from the Official MCP Registry
Design mobile-first presentations — create, edit, preview, and publish from your AI.
Design mobile-first presentations — create, edit, preview, and publish from your AI.
Remote endpoints: streamable-http: https://mcp.flow2.co/
Remote MCP endpoint verified (355ms response). 3 trust signals: valid MCP protocol, requires auth, registry import. No security issues detected.
Endpoint verified · Requires authentication · 2 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Remote servers are capped at 8.0 because source code is not available for review. The score reflects endpoint verification only.
This plugin requests these system permissions. Most are normal for its category.
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"co-flow2-flow2": {
"url": "https://mcp.flow2.co/"
}
}
}From the project's GitHub README.
Design mobile-first presentations — create, edit, preview, and publish from your AI assistant.
This is the official Model Context Protocol server for Flow2. It lets AI assistants like Claude work with your Flow2 account directly: spin up new flows, add and edit screens, drop in blocks, preview the result, and publish — all from a chat prompt.
https://mcp.flow2.co/streamable-httpco.flow2/flow2claude mcp add --transport http flow2 https://mcp.flow2.co/ --scope user
Then run /mcp inside Claude Code to complete the OAuth sign-in.
Settings → Connectors → Add custom connector → URL: https://mcp.flow2.co/. Click Connect to authorize.
In ~/.cursor/mcp.json:
{
"mcpServers": {
"flow2": {
"url": "https://mcp.flow2.co/"
}
}
}
Any client that supports remote streamable-HTTP MCP servers can connect using the URL above. OAuth is handled automatically when the client supports DCR.
The Flow2 MCP server exposes the full flow-authoring surface as tools:
| Tool | What it does |
|---|---|
create_flow | Create a new Flow2 presentation |
update_flow_meta | Rename or update flow-level metadata |
get_flow | Read the current state of a flow |
add_screen | Add a new screen to a flow |
get_screen | Read a screen and its blocks |
delete_screen | Remove a screen from a flow |
add_block | Add a block (text, image, button, etc.) to a screen |
patch_block | Update an existing block's content or styling |
delete_block | Remove a block from a screen |
get_blocks_schema | List available block types and their schemas |
get_preview | Render a preview link for the current flow |
list_jobs / check_job_status | Track long-running operations |
check_credits | Check the remaining credits on your account |
All write tools are annotated with destructiveHint: false where appropriate so AI clients can reason about safety. Read-only tools are marked readOnlyHint: true.
Once the server is connected, try:
The assistant will call the right MCP tools, and you'll see the changes reflected in your Flow2 account in real time.
The server implements OAuth 2.1 with Dynamic Client Registration. When you connect from a new client, it:
/.well-known/oauth-authorization-serverregistration_endpointYou can revoke a client at any time from your Flow2 account settings.
Full details: Privacy Policy · Terms of Service.
MIT — see LICENSE.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.