MCP server that turns a FigJam board into queryable LLM context — read via the Figma API, clustered with geometry + vision. No PDF export.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add figjam --env FIGMA_ACCESS_TOKEN='<FIGMA_ACCESS_TOKEN>' --env LLM_API_KEY='<LLM_API_KEY>' -- npx -y figjam-context-mcp~/.codex/config.toml
[mcp_servers.figjam]
command = "npx"
args = ["-y", "figjam-context-mcp"]
env = { FIGMA_ACCESS_TOKEN = "<FIGMA_ACCESS_TOKEN>", LLM_API_KEY = "<LLM_API_KEY>" }
# codex mcp add figjam --env FIGMA_ACCESS_TOKEN='<FIGMA_ACCESS_TOKEN>' --env LLM_API_KEY='<LLM_API_KEY>' -- npx -y figjam-context-mcp~/.cursor/mcp.json
{
"mcpServers": {
"figjam": {
"command": "npx",
"args": [
"-y",
"figjam-context-mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "<FIGMA_ACCESS_TOKEN>",
"LLM_API_KEY": "<LLM_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"figjam": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"figjam-context-mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "<FIGMA_ACCESS_TOKEN>",
"LLM_API_KEY": "<LLM_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"figjam": {
"command": "npx",
"args": [
"-y",
"figjam-context-mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "<FIGMA_ACCESS_TOKEN>",
"LLM_API_KEY": "<LLM_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"figjam": {
"command": "npx",
"args": [
"-y",
"figjam-context-mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "<FIGMA_ACCESS_TOKEN>",
"LLM_API_KEY": "<LLM_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"figjam": {
"command": "npx",
"args": [
"-y",
"figjam-context-mcp"
],
"env": {
"FIGMA_ACCESS_TOKEN": "<FIGMA_ACCESS_TOKEN>",
"LLM_API_KEY": "<LLM_API_KEY>"
}
}
}
}Environment variables
FIGMA_ACCESS_TOKENLLM_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.