flayr
OnlineNewCreate, schedule and publish social posts to 13 platforms for your brands.
What it can do: 32 tools
whoamiread-only[read-only] Returns who this connection (an OAuth sign-in or an API key) belongs to: userId, the account's current plan tier, and brandId/brandName when the connection is bound to one brand (null = account-wide). Call thlist_brandsread-only[read-only] Lists the brands this connection can file content into and publish through. Use an `id` as `brandId` on create_content, publish, queues and analytics tools; "personal" means the account owner's personal accoucreate_brand[writes flayr data · `write` scope] Creates a new brand in the account owner's organization, the same as "New brand" in the dashboard. Send `name` and optionally `website`, like `{ name: "Dragon Shop", website: "https://brand_profile_getread-only[read-only] A brand's profile (website, companyName, tagline, industry, audience, values, pillars, hashtag sets), its default voice, colors and fonts. `brandId` comes from list_brands; a brand-bound connection may omit ilist_connected_accountsread-only[read-only] The social accounts a brand can post to — the same set publish would use for that `brandId`: platform, handle, display name, health (healthy, needs_reauth, disconnected), whether it is the brand's default foraccount_trial_getread-only[read-only] The connected account's trial: which one it is on (`current.label`, e.g. the 14-day posting trial, a plan trial or a comped plan), the day and days left, the end date, what it falls back to (`current.fallsBacupload_media[writes flayr data · `write` scope] Step 1 of attaching a LOCAL file (video, image or audio) to a draft. Returns a single-use, short-lived `uploadUrl`. Step 2: POST the raw file bytes to it with the file's Content-Type,create_content[writes flayr data · `write` scope] `altText` is a string for one image or one string per carousel slide in images / imageStorageIds order. Creates a DRAFT content item. Nothing is posted. Give `text` plus optional mediaupdate_content[writes flayr data · `write` scope] `altText` edits image descriptions: a string for one image or an ordered array for carousel slides; refused after booking. Edits a draft in place; only the fields you pass change. Anyarchive_content[writes flayr data · `write` scope] Soft-archives an uncommitted draft or failed generation. Keeps its content and media; Restore is available in the Library Archive view. Repeating the call is safe. Refused (409) for redelete_content[DESTRUCTIVE] DESTRUCTIVE: permanently deletes a content item from the library. Posts already live on a platform are not removed. Needs the `write` scope. Ask the user before calling. (Wraps DELETE /api/v2/content/{id}.)get_job_statusread-only[read-only] Status of an async job (combine_clips, render_motion_ad, or an API video generation): pending, processing, completed or failed. For a combine or a motion ad, `resultContentId` is the new draft once completed;publish[PUBLISHES to social accounts · `publish` scope] `altText` overrides image descriptions for this booking: one string per image (array for a carousel). PUBLISHES TO REAL SOCIAL ACCOUNTS. Posts now, or at `scheduledAt` (ISget_postread-only[read-only] A post (`id` = convexPostId from publish, or posts[].id from get_content): status, slot, platforms, its internal labels and per-platform/account instanceLabels, and while it is scheduled the first comment eacupdate_scheduled_post[PUBLISHES to social accounts · `publish` scope] CHANGES WHAT A SCHEDULED POST WILL PUBLISH on real accounts, keeping its slot, accounts, options, labels and draft. `firstComment` sets per-platform first comments (linkedreschedule_post[PUBLISHES to social accounts · `publish` scope] MOVES A SCHEDULED POST to `scheduledAt` (ISO 8601 with a timezone, e.g. "2026-11-19T15:00:00Z"; more than 5 minutes ahead). The booking keeps its id, caption, media, accoucancel_scheduled_post[PUBLISHES to social accounts · `publish` scope] Takes a SCHEDULED post off the platform schedule and marks it cancelled (the draft stays, so it can be published again). Safe to repeat. Refused within 5 minutes of the sllist_failedread-only[read-only] The Schedule → Failed backlog of the brand: one row per platform of a post that did not go out, with its row `id`, postId, contentId, account, slot, lastError, reasonClass and `coverage` ("live" / "rebooked"approvals_listread-only[read-only] The approvals inbox: everything that waits on the user's decision, in one list. `kind` "ad_budget" is an ad agent's request above the owner's ceiling (a spend cap, a spending limit, a campaign budget), with `approvals_decide[PUBLISHES to social accounts · `publish` scope] Decides ONE item from approvals_list (`id`): decision "approve" or "reject", optional `note`. ALWAYS show the user the item's `summary` (e.g. "Monthly ad spend cap: $500.0get_analyticsread-only[read-only] Engagement overview for the last 7, 30 or 90 days. Pro plan or higher. (Wraps GET /api/v2/analytics.)query_insightsread-only[read-only] Read-only analytics query: one `metric` aggregated (median by default) over posts, broken down by up to a few dimensions (platform, weekday, hour, brand, campaign, postType, label:<key>, arm), at a fixed postlist_plansread-only[read-only] The plans flayr sells today: price (USD monthly, USD per year annual), monthly Embers, seats, brands, connected accounts and features. `intervals` lists what start_checkout accepts for each plan; `checkout` sstart_checkout[writes flayr data · `write` scope] Returns a checkout link for a plan from list_plans (`interval` monthly or annual, default monthly). A HUMAN opens it and pays: Stripe Checkout for individual plans, the organization sesubscription_statusread-only[read-only] The current plan and Embers balance of the connected flayr account, with the link where the owner manages billing. (Wraps GET /api/v2/billing/subscription.)agent_signup[writes flayr data · `write` scope] Creates a flayr account for an AI agent, no key or browser needed: sends a 6-digit code to `email` (an inbox you read, e.g. AgentMail). Calling it accepts the flayr Terms of Service anagent_signup_verify[writes flayr data · `write` scope] Checks the emailed code and returns an API key (shown once). New address: the new account's first key (`account: "new"`). Address that already has a flayr account: a NEW key on that acread_contentread-only[read-only] Read content. mode="list" returns one page of summaries (limit, cursor, fields); mode="get" requires id and returns the full item. Use only the chosen mode's arguments. Full mode definitions: describe_tool {"search_toolsread-only[read-only] Finds flayr tools that are not in this list (ads, studio, campaigns, stores, …). Returns name, one-line purpose and toolset. Then call the tool by name, or load its toolset with enable_toolset to get its fullenable_toolsetread-only[read-only] Returns the full definitions (description and input schema) of every tool in one toolset, so you can call them. Call them by name, or through call_tool if your client only calls listed tools. To list a toolsecall_toolRuns any flayr tool, listed or not, with the same scopes, plan checks and confirmations as calling it directly. The inner tool's own risk applies: confirm PUBLISHES or DESTRUCTIVE tools with the user first.describe_toolread-only[read-only] Returns one tool's full description and input schema. Some listed tools are shortened to save tokens: they end with "Full description and schema: describe_tool". Every argument in the full schema is accepted.
Connect it
claude mcp add --transport http flayr https://flayr.social/api/mcpSettings → Connectors → Add custom connector
URL: https://flayr.social/api/mcp{
"mcpServers": {
"flayr": {
"url": "https://flayr.social/api/mcp"
}
}
}{
"servers": {
"flayr": {
"type": "http",
"url": "https://flayr.social/api/mcp"
}
}
}Questions
What does flayr do?
Create, schedule and publish social posts to 13 platforms for your brands. It exposes 32 tools to AI assistants.
What tools does flayr provide?
32 tools, including whoami, list_brands, create_brand, brand_profile_get, list_connected_accounts, account_trial_get, upload_media, create_content, update_content, archive_content, delete_content, get_job_status….
How do I connect flayr to Claude, ChatGPT or Cursor?
Add the remote MCP endpoint https://flayr.social/api/mcp as a custom connector or MCP server. Copy-paste setup is on this page.
Does flayr require an account or API key?
No sign-in was needed to list its tools. Individual tools may still need an account or API key.
Is flayr online?
As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.
Who publishes flayr?
flayr.social. The official MCP Registry verified that the publisher controls this domain before accepting the listing.
Similar in News & Content
-
Parse.ly MCPOnline · sign-in requiredOfficialPopular
Query your Parse.ly content analytics: top content, referrers, campaigns, trends and real-time data.
-
ElfsightOnline · sign-in requiredOfficialPopularNew
Manage Elfsight widgets: browse apps and projects, create, configure and publish widgets.
-
Playgama MCP - Publish & Manage HTML5 GamesOnline · sign-in requiredOfficial
Publish HTML5 games in seconds from an AI agent: audience, monetization, analytics.
-
Trend News AgencyOnlineOfficial
Trend News Agency: search and read 2.6M articles on Azerbaijan, the Caspian and Central Asia.
-
한국일보 뉴스 (Hankookilbo)OnlineOfficial
Hankookilbo (Korean daily) news metadata: titles, dates, sections, bylines, links, and excerpts.
-
KollusOnlineOfficialNew
Query your Kollus video platform in natural language — VOD content, analytics, and docs.