Skip to main content
Glama

broll

The content studio MCP for coding agents. broll gives Claude Code, Codex, and any MCP client real hands for content work: generate media with your own API keys, render videos and carousels deterministically with code, and publish through a draft-first outbox.

The model plans. Code renders. Nothing posts without confirmation.

Why

Every developer running a coding agent hits the same wall: the agent can write the marketing plan, but it can't make the carousel, cut the video, or post it. Existing tools are credit-metered schedulers built for social media managers. broll is built for developers:

  • BYO keys, no markup. Image/video generation uses your OPENAI_API_KEY / GEMINI_API_KEY directly. broll never proxies your inference or resells credits. A built-in mock provider keeps every workflow runnable before you add any keys.

  • Deterministic rendering. Videos and slides are compiled from declarative plans into exact ffmpeg/sharp invocations. Same plan + same inputs = same output. When AI output drifts, the fix is code — so layout, fonts, captions, and branding live in code.

  • Draft-first publishing. Posts are reviewable JSON files in an outbox. publish_post requires confirm: true, validates per-platform rules (char limits, media counts, file sizes) before anything leaves the machine, and reports per-platform results. The export platform always works: it writes a ready-to-post bundle.

Related MCP server: creatorforge

Install

Requires Node 20+ and ffmpeg (brew install ffmpeg).

cd broll
npm install && npm run build

Register with Claude Code (or use the checked-in .mcp.json when working inside this repo):

claude mcp add broll -- node /path/to/broll/dist/index.js

Optional environment:

Variable

Purpose

OPENAI_API_KEY

gpt-image-1 image generation

GEMINI_API_KEY

Imagen images + Veo video generation

BLUESKY_IDENTIFIER / BLUESKY_APP_PASSWORD

live Bluesky posting (use an app password)

MASTODON_ACCESS_TOKEN (+ optional MASTODON_INSTANCE)

live Mastodon posting — no app review, any instance

X_API_KEY / X_API_SECRET / X_ACCESS_TOKEN / X_ACCESS_TOKEN_SECRET

live X posting (free API tier works)

BROLL_HOME

workspace location (default ~/.broll)

BROLL_FFMPEG / BROLL_FFPROBE

explicit binary paths

Brand kit: drop a broll.config.json next to where the server runs (see this repo's for an example) — name, handle, colors, font, logo. Every render picks it up automatically.

Tools

Tool

What it does

broll_status

Workspace, ffmpeg, provider + platform readiness. Call first.

generate_image / generate_video

BYO-key generation → workspace assets (mock fallback when keyless)

import_asset / list_assets / probe_asset

Bring in and inspect media

render_video

Declarative RenderPlan → mp4: clips (video/image/color), trims, cover/contain fits, burned-in titles + timed captions, music bed, 9:16 / 1:1 / 4:5 / 16:9

render_carousel

Branded slide sets (the Instagram/LinkedIn format): kicker, headline, body, accent bar, page numbers, watermark — layout is 100% code

extract_frame

Pull a PNG frame so the agent can visually QA its own render

create_post_draft

Text + media + platforms → validated, reviewable draft in the outbox

list_drafts / publish_post

Inspect the outbox; publish with explicit confirm: true

Try it

npm run smoke

drives the real server through a real MCP client: generates a background, renders a 3-slide carousel and a 9:16 teaser video with captions, extracts a QA frame, then drafts and "publishes" an export bundle — all into ./.broll/.

broll cloud (waitlist)

The local server you're looking at stays MIT and free. broll cloud adds the parts a local server can't do well: the app-review-walled platforms (Instagram, LinkedIn, TikTok) through broll's own approved credentials, schedules that run while your laptop is closed, and a swipe-to-approve inbox on your phone. ~$29/mo when it ships.

Join the waitlist → 👍 issue #1 — subscribers get the launch note; comments set the platform build order.

Safety model

  1. Nothing is published without a draft file on disk first.

  2. publish_post hard-requires confirm: true — agents are instructed to obtain the user's explicit go-ahead.

  3. Constraint violations block publishing; they never auto-truncate your text.

  4. Keys are read from your environment and sent only to their own vendor's API.

Status & roadmap

Early but real: 96 tests including real-ffmpeg integration renders and a full MCP round trip.

  • Bluesky video upload

  • X chunked video upload

  • LinkedIn adapter (needs app review)

  • Mastodon adapter

  • YouTube Shorts via user OAuth

  • Ken Burns / crossfade transitions

  • Word-level caption timing from transcripts

  • npx broll-mcp distribution

Development

npm test          # unit + integration (real ffmpeg)
npm run typecheck
npm run smoke     # end-to-end artifact check

MIT.

Available Tools

14 tools
broll_statusbroll statusA

Report workspace location, ffmpeg availability, configured generation providers, and social platform readiness. Call this first to see what is possible. Pass probe: true to live-verify social credentials (makes real authenticated API calls, posts nothing).

Inputs: probe.

create_post_draftCreate post draftA

Create a reviewable post draft (text + media + target platforms). Validates against per-platform rules (char limits, media counts/sizes) and reports violations. Nothing is published — drafts are files the user can inspect; use publish_post to send.

Inputs: text (required), platforms (required), media.

create_thread_draftCreate thread draftA

Create a multi-post thread draft. On publish, posts chain as replies under the first one (Bluesky reply refs, X in_reply_to). Each post has its own text and up to 4 images, validated per platform. Nothing is published until publish_post with confirm: true.

Inputs: posts (required), platforms (required).

extract_frameExtract frameA

Extract a single PNG frame from a video at a timestamp — use it to visually QA a render.

Inputs: asset (required), atSec.

generate_imageGenerate imageA

Generate image(s) with the user’s own API keys (BYO-key: OpenAI or Gemini; falls back to a labelled mock when no keys are set). Returns workspace asset ids usable in render_video, render_carousel, and post drafts.

Inputs: prompt (required), n, label, aspect, +1 more.

generate_videoGenerate videoA

Generate a short video clip with the user’s own API keys (Gemini Veo when configured; labelled mock otherwise). Expensive with real keys — only call when the user’s workflow needs generated footage.

Inputs: prompt (required), aspect, provider, durationSec.

import_assetImport assetA

Copy a local file (image/video/audio) into the broll workspace and get an asset id for it.

Inputs: path (required), label.

list_assetsList assetsA

List workspace assets (generated, imported, and rendered), optionally filtered by kind.

Inputs: kind.

list_draftsList draftsA

List post drafts in the outbox with status and publish results.

Inputs: no named parameters.

probe_assetProbe assetA

Inspect a media file: duration, dimensions, codecs, streams. Accepts an asset id or absolute path.

Inputs: asset (required).

publish_postPublish postA

Publish a draft to its target platforms. Requires confirm: true — never call this without the user’s explicit go-ahead in the conversation. Platforms without credentials fail independently with setup instructions; "export" always succeeds and writes a ready-to-post bundle.

Inputs: confirm (required), draftId (required), platforms.

render_videoRender videoA

Compile a declarative RenderPlan into an mp4 via ffmpeg — deterministic, brand-aware, no generation keys needed. Clips (video/image/color) are concatenated in order; overlays and captions are burned in; optional music is mixed under clip audio. Returns the rendered asset id.

Inputs: plan (required).

set_profileSet profileA

Update the Bluesky profile (display name, bio, avatar image) — merges with the existing profile, never clobbers other fields. Requires confirm: true because it changes the public account.

Inputs: confirm (required), bio, avatarAsset, displayName.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 14 tools

    Disambiguation5/5

    Each tool targets a distinct resource or action: status, generation, import/list/probe assets, rendering, draft creation, publishing, and profile update. There is no functional overlap, even among similar pairs like generate_image/generate_video and render_video/render_carousel.

    Naming Consistency4/5

    Almost all tools follow a consistent verb_noun snake_case pattern (generate_image, list_assets, publish_post). The only deviation is 'broll_status', which uses a domain prefix plus noun rather than a verb, creating a minor inconsistency.

    Tool Count5/5

    14 tools is within the ideal 3-15 range and matches the server's broad scope (asset generation, management, rendering, drafts, publishing, profile). Each tool serves a distinct step in the workflow, and the count feels well-proportioned.

    Completeness4/5

    The tool surface covers the full content creation and publishing pipeline: asset generation/import/inspection, rendering, draft creation, publishing, and profile updates. Minor gaps include no explicit draft update/delete or asset deletion, but agents can work around these with list/create operations.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that automates short-form video production for TikTok, Instagram Reels, and YouTube Shorts, using AI agents and behavioral science to generate production-ready videos from a topic and vibe.
      1
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server for creative generation and video production, letting AI agents author declarative animations, render deterministic frames, and measure output quality with perception instruments for brand and accessibility conformance.
      Apache 2.0