@kolbo/mcp

Personal fonts

Browse My fonts with list_fonts({source:"custom"}) (the default), or the read-only Font collection with source:"global". Use source:"all" to search both. Mix up to three family IDs across both sources in the same generation; inspect actual styles/scripts with get_font. Collection fonts do not need uploading and cannot be renamed or deleted by users.

Use list_fonts / get_font to discover My Fonts. Local stdio clients upload one OTF/TTF/WOFF2 (up to 5 MiB) with upload_font; remote shell clients use create_font_upload_ticket, and browser clients use font_upload_widget. Poll get_font_upload_status until ready, then pass the returned family ID in font_ids to image creation/editing or image-mode Creative Director. rename_font and delete_font manage the library.

Only models reporting supports_custom_fonts: true accept these selections. Fonts and backend-generated specimens never go through media upload. See Personal Fonts. Availability requires a published client and deployed backend containing these tools; source changes alone do not update installed clients.

No-background images

generate_image and generate_image_edit accept background: "transparent" for models whose list_models record reports supports_transparent_background: true. Kolbo also appends the exact phrase no background once to the effective prompt, while the structured setting requests the native alpha channel through the configured provider route. Use output_format: "png" or "webp" (PNG is selected automatically when omitted). Prompt wording alone is not sufficient, and unsupported models reject the request instead of silently returning an opaque image.

Use Kolbo AI as native tools in Claude Code and Claude Desktop via MCP (Model Context Protocol).

Generate images, videos, music, speech, sound effects, multi-scene campaigns, and conversational chat — all from natural language in your coding environment. 100+ AI models behind Smart Select routing, with reusable Visual DNA profiles for character/style consistency.

✨ Interactive widgets (v1.30+): in claude.ai, Claude Desktop, and Codex Desktop, generations render as live Kolbo cards — real-time progress with model + settings chips, an inline result gallery / video or audio player, and one-click Animate · Edit · Recreate · Download actions. Multi-audio generations render every track with its own player and Download button. Library and model searches render as browsable grids with audio preview. Text-only clients (Claude Code, Codex CLI, Cursor) keep the classic text responses.

Set up — paste one prompt, or one config block (keyless, no API key)

Flow sessions and nodes

Flow tools create, inspect, precisely edit, organize, validate and run saved node workflows in an explicit project. Use get_flow_schema, get_flow_session and revision-checked update_flow_session for prompts, Assistant system prompts, settings, groups and connections. Runs use explicit aggregate credit limits and persisted run IDs. Compatible Flow API routes are required. See Flow MCP workflow and contract.

Easiest: paste this prompt to your AI

Copy this and paste it to Claude, ChatGPT, Cursor, or any AI assistant — it installs Kolbo itself (picks local config or remote connector based on what it can do):

Connect the Kolbo AI MCP server (generate images, video, music and more).

- If you can run terminal commands (Claude Code, Cursor, Claude Desktop, or any local setup): run "npx -y @kolbo/mcp install" — it auto-configures Kolbo in the right place. If you can't run it, give me the command to run. Then I'll restart the app.
- If you're a browser chat (claude.ai, ChatGPT): add a custom connector with URL https://api.kolbo.ai/mcp under Settings → Connectors, then Connect → log in → Allow.

No API key needed — on first use a Kolbo login opens in my browser and I click Allow. When set up, confirm Kolbo is connected and offer to generate a test image of a sunset.

Or set it up yourself — one command

Run this once — it sets up the full Kolbo experience (the MCP tools and the routing skill) for every installed agent (Claude Desktop, Claude Code, Cursor), keyless:

npx -y @kolbo/mcp install

Or add the config by hand — this block is identical for every MCP client and carries no API key (on first use it logs you in via the browser):

{
  "mcpServers": {
    "kolbo": {
      "command": "npx",
      "args": ["-y", "@kolbo/mcp@latest"]
    }
  }
}

Restart your app, then ask it to generate something. The first time, a Kolbo login opens in your browser — click Allow (no API key to create). Prefer an API key? Create one at app.kolbo.ai/developer and add "env": { "KOLBO_API_KEY": "kolbo_live_..." } to the block above.

Browser-only (claude.ai / ChatGPT / Codex): connector + skill

1. Add the custom connector https://api.kolbo.ai/mcp under Settings → Connectors, then Connect → log in → Allow.
2. Download the Skill and upload it (Claude.ai: Settings → Features → Skills; ChatGPT/Codex: Settings → Skills). Codex CLI: unzip into ~/.codex/skills/.

The Skill is the canonical routing layer. Without it the tools still work, but the model will not load Seedance / Visual DNA / filmmaking rules.

Optional upgrade: add the Kolbo skill for slash-commands + smart routing

The config above is all you need. If you want one-word slash-commands (/kolbo:marketing-studio, /kolbo:product-photoshoot, …) and automatic routing to the best tool with the right defaults, install the Kolbo skill on top — it's an enhancement layer, not a requirement:

# Claude Code plugin (canonical skill + MCP configuration)
claude plugin marketplace add Zoharvan12/kolbo-claude-plugin
claude plugin install kolbo@kolbo

# Skill only — installs the bundled official skill without changing MCP settings
npx -y @kolbo/mcp@latest skill

The skill-only command installs the canonical single kolbo skill and does not change MCP configuration. The Claude Code plugin and npx -y @kolbo/mcp install routes configure MCP as well. Official installer-created skill folders are marked as Kolbo-managed and refresh automatically when the MCP server starts on a newer package; unmarked or hand-authored folders are never overwritten. The canonical skill ships inside Kolbo Code, so however you connect, the behavior matches. See the full setup guide at docs.kolbo.ai/developer-api/claude-code-skill.

Use it

Just ask your agent naturally:

Generation

• "Generate an image of a sunset over mountains"
• "Create a 5-second video of waves crashing"
• "Build a 4-scene storyboard for a coffee shop ad"
• "Remove the background from this image"
• "Make a lo-fi hip hop beat"
• "Read this out loud with a British female voice"

Marketing & UGC

• "Make me a UGC ad for my sneaker brand — 9:16, talking-head style"
• "TV spot for my new beverage, 15 seconds, cinematic"
• "Unboxing video for this product photo"

Brand & product imagery

• "Pinterest pin for my candle brand, cottagecore mood"
• "Hero banner for my landing page, wide format"
• "Lifestyle shot of my product in a kitchen"
• "4 ad creative variants for Meta and TikTok"

Marketplace listings

• "Generate Amazon main image + 5 secondary images for my product"
• "Full A+ content set for my Shopify listing"

Analysis & utility

• "Ask Claude about the latest AI news with web search on"
• "Analyze this video and tell me what prompts are shown on screen"
• "What's in this image?"
• "Create a Visual DNA profile called 'Alex' from these images"
• "Use the same brand as last time" (loads a persisted brand kit from the workspace)

Without the optional skill, the config block alone already exposes every tool — you just describe what you want. With the skill installed, each of these is also routed to the right MCP tool with the right defaults — UGC mode picks 9:16 + sound-off + no-captions, marketplace mode enforces compliance (pure white bg, no text, no props), product photoshoot mode uses the right aspect for the platform (2:3 Pinterest, 16:9 hero banner, 1:1 IG feed), etc. The routing logic is shared with Kolbo Code, so the behavior is identical however you connect.

Available Tools

Generation

Every image/video/creative-director tool accepts visual_dna_ids and moodboard_id for character/style consistency across outputs — you can compose create_visual_dna → generate_image (with the DNA applied server-side) in a single agent turn. generate_creative_director also accepts moodboard_ids plural for blending.

Every generation tool also accepts an optional resolution arg. Images use "1K" (~1024px) / "2K" (Full HD) / "3K" (QHD) / "4K" (UHD); videos use vertical-pixel tiers like "720p" / "1080p" / "1440p" / "2160p". Values are model-dependent — call list_models and read the chosen model's supported_resolutions and resolutionMultipliers. Omit to use the model default.

Every generation tool also accepts an optional project_id arg that routes the generation into a specific project (owned or shared with edit+). Call list_projects to discover IDs. When omitted, generations land in the user's auto-created "API Generations" project. project_id is per-call, NOT sticky — pass it on every call once the user names a working project. Misplaced work is recoverable via move_media / move_session.

Chat & Vision

Visual DNA (reusable character/style/product profiles)

Moodboards

Color DNA — sticky, account-wide: the ACTIVE palette strict-grades every generation until deactivated. Opt a single generation out with skip_color_palette.

Media Library

Artifacts

SYNCI Music Library (licensed production music)

Stock Library (multi-source stock media: Pexels, Pixabay, Sketchfab 3D, Music)

Blender Bridge

Premiere Pro & After Effects Bridge Requires the Kolbo Studio panel open in Premiere Pro or After Effects with AI agents switched on in its header. Every edit is approved by the editor inside the panel; scripts are shown in full before they run.

DaVinci Resolve Bridge Requires DaVinci Resolve Studio with the Kolbo plugin open (Workspace → Workflow Integrations → Kolbo AI) and AI agents switched on in its header. Every edit is approved by the editor inside the plugin; scripts are shown in full before they run.

Discovery & Account

Environment Variables

Both are optional — the local install logs in via the browser on first use.

Links

• API Documentation
• Kolbo AI Platform
• Get API Key

Chat thinking level

chat_send_message accepts optional thinking_level, using an ID from list_models with type: "text". The server validates it against the resolved model; omitted or invalid values use thinkingDefault. Existing safeguards and legacy deep_think take precedence. Discover allowed levels through thinkingLevels; no package update is required when the server changes a model capability. For the Auto model, optional routing_mode accepts fast, balanced, or smart; omitted uses the server default of balanced.

Agentic Video Editor

create_video_editor_session also accepts optional advanced session_data instead of clips/audio/texts. Read the schema and saved revision before editing. Changes affect saved state; reload an already-open editor before manual editing. Existing create/export names and arguments remain supported.

URL downloads

download_media_from_url starts a server download for a public media page URL. Use get_download_status with the returned job_id (not get_generation_status) and wait for completed before using resultUrl. cancel_download cancels an active job. This produces a cloud file and saves it to the account library when library sync succeeds; it does not write to the caller's computer. Video returns a verified MP4, audio returns MP3; maximum 500 MB. Existing upload_media still handles local/direct-file uploads. SDK routes reuse the authenticated utility pipeline at POST /v1/downloads, GET /v1/downloads/:jobId, and DELETE /v1/downloads/:jobId.

Video-edit widgets keep source-video and mask-video previews, image references, and audio references through generation and completion. Click a video thumbnail to inspect the source. Local edit inputs preview through their uploaded CDN URLs.