generate_objectLABSCO SUMMARY
The Figma and Magic connectors are placeholders — read that before planning around them.
The README is explicit: those files contain placeholders and need real API calls and MCP client logic written before the integration tools do anything. What works today is the Vercel AI SDK side. The intended pattern is orchestration in the editor — call the Figma server, then the Magic server, then this one — rather than server-to-server calls, and the composite tool that would do it directly is present in the code but not the supported path.
What it is
An MCP server wrapping core Vercel AI SDK functions so an editor assistant can call them alongside other servers, rather than reimplementing structured generation in the editor.
What you get
- Tools wrapping Vercel AI SDK Core functions, including
generate_objectfor structured output andgenerate_ui_component set_tool_category, a meta-tool that switches which category of tools is active — a way to keep the number of exposed tools inside what Cursor handles well- A deployment path to Smithery: a
Dockerfileandsmithery.yamlship with the project, and API keys are supplied at deploy time - Both transports covered — stdio locally, or SSE when
TRANSPORT_TYPEsays so
Requirements
Node.js v20 or later, npm and git; the project is vercel-ai-sdk-mcp-project, version 1.0.0. Clone it, npm install, npm run build, then npm run start. OPENAI_API_KEY is required for the AI SDK tools; ANTHROPIC_API_KEY is optional. FIGMA_API_KEY and TWENTY_FIRST_API_KEY are only needed once the corresponding connectors are implemented. Locally the config points at dist/index.js; deployed, Cursor runs it through the Smithery CLI.
Setup effort
Build from source — git clone https://github.com/chiziuwaga/vercel-ai-sdk-mcp-project.git
USE CASES
01
Getting structured output instead of prose
Call the AI SDK's object generation from the editor and get a typed result back.
02
Generating a UI component inside the editor session
Pass the accumulated context to the component generation tool as the last step of a workflow.
03
Keeping the tool list short enough for Cursor
Switch the active category so only the tools you need for this task are exposed.
3 tools
Listed in project docs. Your client may show a different list.
generate_ui_componentset_tool_categoryBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
OPENAI_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/chiziuwaga/vercel-ai-sdk-mcp-project.git
cd vercel-ai-sdk-mcp-project
npm install
npm run build
npm run startMCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"vercel-ai-sdk-mcp": {
"command": "node",
"args": [
"dist/index.js"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"FIGMA_API_KEY": "${FIGMA_API_KEY}",
"TWENTY_FIRST_API_KEY": "${TWENTY_FIRST_API_KEY}",
"TRANSPORT_TYPE": "stdio"
}
}
}
}Put this in the .cursor/mcp.json of the cloned project and open that folder as your Cursor workspace — dist/index.js is relative to the workspace root. In a global Cursor config, use the absolute path to dist/index.js instead. The ${…} keys must be set in the environment Cursor starts from.
