Can I use Vega-Lite as a CLI?

Yes. KosmoKrator exposes a Vega-Lite CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Vega-Lite through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Vega-Lite tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Vega-Lite credentials stored?

Vega-Lite credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Vega-Lite MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

rendering

Vega-Lite CLI for Coding Agents

Use the Vega-Lite CLI for coding agents with headless JSON commands, schema discovery, credentials, and permission controls.

1 functions 0 read 1 write No credentials auth

Submit Vega-Lite feedback View package source

Vega-Lite CLI for Coding Agents

Let coding agents discover schemas and execute integration functions through CLI commands or MCP.

Use this pattern when another coding agent needs exact commands and schema discovery. The Vega-Lite CLI uses the same integration registry as the TUI, Lua runtime, and MCP gateway, but returns predictable command output for automation.

Command Shape

# Vega-Lite CLI for Coding Agents
kosmokrator integrations:configure vegalite --enable --read allow --write ask --json
kosmo integrations:call vegalite.render_vegalite '{"spec":"example_spec","title":"example_title","width":1}' --json

Discovery Before Execution

Agents and scripts can inspect Vega-Lite docs and schemas before choosing a function.

kosmo integrations:docs vegalite --json
kosmo integrations:docs vegalite.render_vegalite --json
kosmo integrations:schema vegalite.render_vegalite --json
kosmo integrations:search "Vega-Lite" --json
kosmo integrations:list --json

Useful Vega-Lite CLI Functions

Function	Type	Parameters	Description
`vegalite.render_vegalite`	Write	spec, title, width	Render a Vega-Lite visualization to a PNG image. Pass a complete Vega-Lite JSON specification and get back a markdown image embed. IMPORTANT: Always use inline data with "data": {"values": [...]}. Never use "data": {"url": "..."}. Example spec: { "$schema": "https://vega.github.io/schema/vega-lite/v5.json", "data": {"values": [ {"category": "A", "value": 28}, {"category": "B", "value": 55}, {"category": "C", "value": 43} ]}, "mark": "bar", "encoding": { "x": {"field": "category", "type": "nominal"}, "y": {"field": "value", "type": "quantitative"} } } Supported mark types: bar, line, point, area, rect, circle, square, arc, text, tick, rule, trail, boxplot. Always include "type" in encoding channels: "quantitative", "nominal", "ordinal", or "temporal".

Automation Notes

Use --json for machine-readable output.
Keep credentials out of argv by using environment variables or stored KosmoKrator configuration.
Configure read/write policy before unattended runs; use --force only for trusted automation.
Use the MCP gateway instead when the agent needs dynamic tool discovery inside a conversation.

Related Vega-Lite CLI Pages

CI Vega-Lite CLI for CI. Cron Jobs Vega-Lite CLI for cron jobs. Shell Scripts Vega-Lite CLI for shell scripts. Headless Automation Vega-Lite CLI for headless automation.