Lets agents save fetched data and render visualizations of it using the Vega-Lite specification format.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add vega-lite -- uv --directory /absolute/path/to/mcp-datavis-server run mcp_server_vegalite --output_type png~/.codex/config.toml
[mcp_servers.vega-lite]
command = "uv"
args = ["--directory", "/absolute/path/to/mcp-datavis-server", "run", "mcp_server_vegalite", "--output_type", "png"]
# codex mcp add vega-lite -- uv --directory /absolute/path/to/mcp-datavis-server run mcp_server_vegalite --output_type png~/.cursor/mcp.json
{
"mcpServers": {
"vega-lite": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp-datavis-server",
"run",
"mcp_server_vegalite",
"--output_type",
"png"
]
}
}
}.vscode/mcp.json
{
"servers": {
"vega-lite": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp-datavis-server",
"run",
"mcp_server_vegalite",
"--output_type",
"png"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"vega-lite": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp-datavis-server",
"run",
"mcp_server_vegalite",
"--output_type",
"png"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"vega-lite": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp-datavis-server",
"run",
"mcp_server_vegalite",
"--output_type",
"png"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"vega-lite": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp-datavis-server",
"run",
"mcp_server_vegalite",
"--output_type",
"png"
]
}
}
}