Skip to main content
Glama

FluxSocial

Server Details

Write, design and publish Instagram and TikTok posts from your AI assistant.

Ownership verified
Status
Healthy
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-03-26
URL

TDQS

Score is being calculated.

Available Tools

15 tools
cancel_scheduled_postInspect

Cancel a previously scheduled post. Only works for posts with status SCHEDULED.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesSuggestion ID of the scheduled post to cancel
check_post_statusInspect

Check whether a suggestion has been posted and to which platforms. Returns posting status per platform with post URLs.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesSuggestion ID to check
check_video_statusInspect

Check the status of an async video generation. Call this after generate_video to poll for completion. When status is 'completed', the response includes the videoUrl. Poll every 10-15 seconds.

ParametersJSON Schema
NameRequiredDescriptionDefault
operationIdYesThe operationId returned by generate_video
generate_contentInspect

Generate social media post suggestions with AI-written captions, titles, hashtags, and platform-specific adaptations. Returns multiple text suggestions (title, body, tags). For IMAGE format, each suggestion includes imagePrompts — use generate_image to create visuals. For VIDEO format, each suggestion includes videoPrompt (single-scene) or videoScenes (multi-scene) — use generate_video with the video prompt. After the user picks a suggestion, generate the visual separately. Use list_businesses first to get a valid businessId.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesDescribe the content topic, e.g. 'Morning yoga tips for beginners' or 'New product launch announcement for our coffee shop'
languageNoOverride the output language (e.g. 'he', 'en', 'es'). If omitted, content is generated in the language matching the business's Content DNA / posting history. Only set this when the user explicitly requests content in a different language than their usual posts.
businessIdYesBusiness ID to generate for. Call list_businesses first to get this.
contentFormatNoTarget media format: IMAGE (visual post with caption), VIDEO (short video/reel), CAROUSEL (multi-image), REEL (short-form video), STORY (ephemeral), TEXT (caption only). Defaults to IMAGE.
useContentDNANoAnalyze the business's past viral posts to match their proven tone and style. Defaults to false.
suggestionCountNoNumber of content suggestions to generate (1-6). Defaults to 4. Use 2 for quick scheduling flows where the user already knows what they want.
generate_imageInspect

Generate an AI image for a specific content suggestion. Costs 50 credits. When called without a customPrompt, the API automatically uses the suggestion's stored imagePrompts[imageIndex] — no need to pass the prompt manually. Call this after generate_content once the user picks a suggestion. For carousel posts, use imageIndex for each slide (0-based).

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesSuggestion ID to generate an image for (from generate_content)
imageIndexNoImage slide index (0-based). Use 0 for single images, 0-N for carousel slides. Defaults to 0.
customPromptNoOptional custom image prompt. If omitted, uses the auto-generated prompt from the suggestion's Content DNA analysis.
generate_videoInspect

Generate an AI video using Google Veo 3. Costs 500 credits per ~8 seconds. Video generation is ASYNC — this returns an operationId immediately. You must then poll check_video_status until the video is ready (typically 30-120 seconds). Best for Reels, TikToks, and Stories.

ParametersJSON Schema
NameRequiredDescriptionDefault
styleNoVisual style. Default: social (optimized for social media).
promptYesDescribe the video scene. Include subject, action, camera movement, and mood. E.g. 'Cinematic close-up of latte art being poured, warm morning light, shallow depth of field, 9:16 vertical'
durationNoDuration in seconds. Veo 3 supports 4, 6, or 8 seconds (default 8). Cost scales linearly.
aspectRatioNo9:16 for TikTok/Reels/Stories (vertical), 16:9 for YouTube (horizontal). Default: 9:16.
get_contentInspect

Retrieve a previously generated content suggestion by its ID. Returns the full suggestion including title, body, tags, images, and any posts made from it.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesSuggestion ID returned by generate_content
get_credit_balanceInspect

Check your remaining FluxSocial credit balance. Credits are consumed by content generation (text: 5-20, images: 50, videos: 500 credits).

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

get_optimal_timeInspect

Get the AI-recommended optimal posting time based on Content DNA analysis and platform engagement patterns. Returns a suggested datetime, confidence score, and reasoning. Use the returned scheduledDateTime with schedule_content.

ParametersJSON Schema
NameRequiredDescriptionDefault
accountIdsNoOptional list of specific account IDs to narrow the analysis
businessIdYesBusiness ID to analyze
list_accountsInspect

List the user's connected social media accounts (Instagram, TikTok, etc.). Each account has an id, platform, username, and follower count. Use this to find accountIds for post_content.

ParametersJSON Schema
NameRequiredDescriptionDefault
businessIdNoOptional: filter accounts by business ID
list_businessesInspect

List the user's businesses. Each business represents a brand or project (e.g. 'My Yoga Studio', 'Downtown Café') with its own social accounts and content. Use the returned business ID for generate_content.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

post_contentInspect

Publish content immediately to one or more social media platforms. For scheduling at a future time, prefer the dedicated schedule_content tool. Use list_accounts first to get valid accountId and platform values. For image posts, call generate_image first to create the visual.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesSuggestion ID to publish
targetsYesOne or more platform targets to post to simultaneously
scheduledForNoISO 8601 date-time to schedule for future publishing (e.g. "2025-12-25T10:00:00Z"). Omit to post immediately. Prefer schedule_content for scheduling.
preview_costInspect

Preview the credit cost for a generation before running it. Use this to check if the user has enough credits.

ParametersJSON Schema
NameRequiredDescriptionDefault
typeYesGeneration type: 'text' for captions/scripts (5-20 credits), 'image' for AI-generated visuals (50 credits), 'video' for AI video clips (500 credits)
schedule_contentInspect

Schedule content for publishing at a specific future date and time. Provide an ISO 8601 datetime (e.g. "2025-12-25T10:00:00Z"). Use get_optimal_time to find the best posting time based on Content DNA analysis. Posts are published within ~2 minutes of the scheduled time.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesSuggestion ID to schedule
targetsYesPlatforms to post to
scheduledForYesISO 8601 date-time for when to publish (e.g. "2025-12-25T10:00:00Z"). Must be in the future.
upload_mediaInspect

Upload a user's own photo or video for posting. The user must provide an HTTPS link to their media (e.g. from Google Drive, Dropbox, iCloud, Imgur, or any public URL). Processes images to Instagram-optimal 1080x1080 and uploads to blob storage. Creates a suggestion ready for post_content or schedule_content. Costs 0 credits. If the user pastes an image directly instead of a link, ask them to share the image as a public URL (e.g. upload to Google Photos or Imgur and share the link).

ParametersJSON Schema
NameRequiredDescriptionDefault
tagsNoOptional hashtags (without # prefix).
titleNoOptional title. Defaults to first 50 characters of caption.
captionYesCaption text for the post.
mediaUrlNoHTTPS URL to the image or video. The user should share a public link from Google Drive, Dropbox, iCloud, Imgur, etc. Max 8MB images, 100MB videos. For CAROUSEL use mediaUrls instead.
mediaUrlsNoFor CAROUSEL only: array of 2-10 HTTPS image URLs.
businessIdYesBusiness ID. Call list_businesses first to get this.
contentFormatYesMedia format: IMAGE (photo post), VIDEO (video post), CAROUSEL (multi-image), REEL (short video), STORY (ephemeral). TikTok only accepts VIDEO.

Tool Schema Changelog

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

  1. 15 tool updates
    • First observedcancel_scheduled_post
    • First observedcheck_post_status
    • First observedcheck_video_status
    • First observedgenerate_content
    • First observedgenerate_image
    • First observedgenerate_video
    • First observedget_content
    • First observedget_credit_balance
    • First observedget_optimal_time
    • First observedlist_accounts
    • First observedlist_businesses
    • First observedpost_content
    • First observedpreview_cost
    • First observedschedule_content
    • First observedupload_media

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    Enables AI assistants to schedule and publish social media posts to platforms like Instagram, TikTok, YouTube, LinkedIn, Facebook, X, Threads, and Pinterest using natural language.
    33
    586 npm
    4
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    AI-powered social media posting across 14 platforms. Post to Twitter, Instagram, TikTok, Facebook, LinkedIn, YouTube and more with one command. AI adapts content per platform, schedules posts, and generates 30-day content calendars.
    6
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Lets any AI agent post to TikTok, Instagram, YouTube, X, LinkedIn, Bluesky, Telegram, Mastodon and Discord through a single post_to_social tool. Connect an account once, then publish everywhere.
    2
    74 npm
    MIT
Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources