Flayr MCP server

• Registry namesocial.flayr/flayrverified in the MCP registry

The registry name sits under flayr.social. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-30
• Tools57
• Server calls itselfflayr
• Server version1.2.0
• Protocol version2025-06-18

On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 172 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 4 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer847 ms
• Space in an agent's context≈ 20,425 tokensthe definitions of all its tools (57), which an agent carries on every turn
• Tool definitionsB · 87 of 100
• Typed results0 of 57 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 43 of 57

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• whoami

  [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 this first to learn…

• list_brands

  [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 accounts. A connection…

• list_connected_accounts

  [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) and whether flayr can post there right now (`postable`…

• list_youtube_playlists

  [read-only] Playlists of the YouTube channel(s) a brand publishes to. Use a playlist id as `youtube.playlistId` on create_content or publish. (Wraps GET /api/v2/youtube/playlists.)

• list_pinterest_boards

  [read-only] Boards of the Pinterest account(s) a brand publishes to. Use a board id as `pinterest.boardId` on publish. A board is required; the one you pick is remembered as the brand's default for next time, and a publish that uses the…

• upload_media

  [writes flayr data · `write` scope] Step 1 of attaching a LOCAL file (video or image) 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, e.g. `curl -X POST -H…

• list_content

  [read-only] Lists content items (drafts), newest first. Each carries `postState` ("posted" / "scheduled" / null) and `posts[]` (up to 5): where it went out, per platform, with status, live URL and failure reason. (Wraps GET…

• get_content

  [read-only] One content item plus its live posting status: `postState` and `posts[]` (up to 20, newest first) with each post's status (scheduled · publishing · published · partial · failed · review_held · held), scheduledAt, and…

• create_content

  [writes flayr data · `write` scope] Creates a DRAFT content item. Nothing is posted. Give `text` plus optional media (`videoUrl` / `imageUrl`, or `videoStorageId` / `imageStorageId` from upload_media), target `platforms`, `brandId` (from…

• update_content

  [writes flayr data · `write` scope] Edits a draft in place; only the fields you pass change. Any media field replaces the draft's media as a set (keeps the id, so queue items still point at it). Refused (409) for archived or…

• delete_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}.)

• combine_clips

  [writes flayr data · `write` scope] Extends a video draft (`id`) with more clips and image cards into ONE finished video, rendered by flayr and saved as a NEW linked draft (same brand, caption copied, credits merged, labelled…

• get_job_status

  [read-only] Status of an async job (combine_clips, or an API video generation): pending, processing, completed or failed. For a combine, `resultContentId` is the new draft once completed; a failed combine is refunded automatically. Poll…

• publish

  [PUBLISHES to social accounts · `publish` scope] PUBLISHES TO REAL SOCIAL ACCOUNTS. Posts now, or at `scheduledAt` (ISO-8601, future). Prefer `contentId` (a draft from create_content: its text and media become the post) over inline…

• get_post

  [read-only] A post (`id` = convexPostId from publish, or posts[].id from get_content): status, slot, platforms, and while it is scheduled the first comment each platform will publish and whether it can be changed now. (Wraps GET…

• update_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 (linkedin, facebook…

• cancel_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 slot, and when the…

• list_reviews

  [read-only] Scheduled posts waiting for (or given) a human sign-off, oldest slot first. `canApprove` tells whether THIS connection may approve each one. (Wraps GET /api/v2/reviews.)

• decide_review

  [PUBLISHES to social accounts · `publish` scope] decision "approve" sends a held post to the platform for its slot (GOES LIVE) — needs the explicit `review` scope (admin does not include it) and never works on a post the same connection…

• list_approvals

  [read-only] Content held for approval that waits on the account owner's decision, newest first: posts filed with publish `requiresApproval: true`, drafts submitted for review, and workflow runs parked at an approval gate. `kind` is…

• decide_approval

  [PUBLISHES to social accounts · `publish` scope] Same rules as the dashboard: only the assigned approver may decide. On a "workflow" approval, decision "approve" resumes the parked run, whose next steps may publish (GOES LIVE); "reject"…

• list_queues

  [read-only] Posting (drip) queues of one brand. A queue posts one item every cadenceHours at timeOfDay in its timezone, keeping `lookahead` items booked at the platform. (Wraps GET /api/v2/queues.)

• get_queue

  [read-only] A queue and its items in order, with each item's state (queued · publishing · scheduled · posted · failed · skipped), booked or projected slot, and attribution status. (Wraps GET /api/v2/queues/{id}.)

• create_queue

  [PUBLISHES to social accounts · `publish` scope] Creates a posting queue. Once items are added it BOOKS REAL POSTS on the given platforms on its cadence (default daily 19:00 America/Chicago, 2 booked ahead). Use `startsAt` to hold…

• update_queue

  [PUBLISHES to social accounts · `publish` scope] `status: "paused"` stops new bookings (already-booked posts stay booked); "active" resumes. Other fields (platforms, cadenceHours, timeOfDay, lookahead, startsAt, name) apply from the next…

• delete_queue

  [DESTRUCTIVE] DESTRUCTIVE: deletes the queue (its drafts stay in the library). With posts booked at the platform it is refused (409) unless `unschedule: true`, which first deletes those platform posts. Needs the `publish` scope (or admin)…

• add_queue_items

  [PUBLISHES to social accounts · `publish` scope] Appends drafts (content ids) to the end of a queue — they will be BOOKED AND POSTED on the queue's schedule. Use `contentIds`, or `items` for a per-item YouTube title or platforms. Drafts…

• queue_item_action

  [PUBLISHES to social accounts · `publish` scope] `action`: "skip" passes over a queued item; "retry" puts a failed/skipped item back in line; "unschedule" deletes a booked platform post and puts the item back in line. Also `youtubeTitle`…

• remove_queue_item

  [DESTRUCTIVE] DESTRUCTIVE: removes an item (the draft stays in the library). A booked (`scheduled`) item is refused (409) unless `unschedule: true`, which deletes its platform post first. Needs the `publish` scope (or admin) on the Agency…

• reorder_queue_items

  [PUBLISHES to social accounts · `publish` scope] Send every waiting (queued) item id exactly once, in the new order. Booked, posted, failed and skipped items keep their places. Needs the `publish` scope (or admin) on the Agency plan or…

• get_analytics

  [read-only] Engagement overview for the last 7, 30 or 90 days. Pro plan or higher. (Wraps GET /api/v2/analytics.)

• query_insights

  [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 post age `window` (48h…

• compare_labels

  [read-only] Splits every labelled post by the values of one label key (e.g. key "cut" → cut:opus vs cut:raw) and reports medians with n per group at the 48h / 7d snapshot. Descriptive, not a significance test. Pro plan or higher. (Wraps…

• list_experiments

  [read-only] A/B experiments. Content joins one by carrying the label `experiment:<id>` plus `<compareKey>:<variant>`. (Wraps GET /api/v2/experiments.)

• get_experiment

  [read-only] One experiment: hypothesis, variants, compareKey, window and status. (Wraps GET /api/v2/experiments/{id}.)

• create_experiment

  [writes flayr data · `write` scope] Creates an A/B experiment. Then tag drafts with its `label` (experiment:<id>) and `<compareKey>:<variant>` via update_content `labels`, publish them, and read get_experiment_results. (Wraps POST…

• update_experiment

  [writes flayr data · `write` scope] Changes an experiment's fields (e.g. status "running" / "done", endAt, notes). Only the fields you pass change. (Wraps PATCH /api/v2/experiments/{id}.)

• delete_experiment

  [DESTRUCTIVE] DESTRUCTIVE: deletes the experiment record (content keeps its labels). Ask the user before calling. (Wraps DELETE /api/v2/experiments/{id}.)

• get_experiment_results

  [read-only] The experiment's posts split by its compareKey, with the leading variant by its primary metric and n per arm. Small samples: read medians with their n. (Wraps GET /api/v2/experiments/{id}/results.)

• list_text_templates

  [read-only] Reusable text shapes per brand: sections, length targets, hook patterns, CTA slots and guardrails. Use one to shape a draft's text before create_content. (Wraps GET /api/v2/text-templates.)

• get_text_template

  [read-only] One format (text template) with its full structure and example. (Wraps GET /api/v2/text-templates/{id}.)

• create_text_template

  [writes flayr data · `write` scope] Creates a reusable format (text template) in a brand. (Wraps POST /api/v2/text-templates.)

• update_text_template

  [writes flayr data · `write` scope] Changes a format; only the fields you pass change. `archived: true` hides it. (Wraps PATCH /api/v2/text-templates/{id}.)

• delete_text_template

  [DESTRUCTIVE] DESTRUCTIVE: deletes a format (drafts started from it keep their text). Ask the user before calling. (Wraps DELETE /api/v2/text-templates/{id}.)

• list_attribution_rules

  [read-only] The brand's "posts like this must carry a credit" rules and its mode (flag / push_down). In push_down mode publish refuses or holds a post missing a required credit — add `credits` with update_content first. (Wraps GET…

• list_share_rules

  [read-only] The brand's share rules: "when <account> publishes, reshare to <accounts> (or comment on it) after N minutes with text T", each with its approval mode. (Wraps GET /api/v2/automations/reshare-rules.)

• create_share_rule

  [PUBLISHES to social accounts · `publish` scope] Creates a rule that reshares (or comments on) every new post of the source accounts. Defaults to needs_approval: each fire waits for approve in act_on_publish_action. Only LinkedIn (native…

• list_publish_actions

  [read-only] Pending, sent and failed comments-after-publish and reshares of the brand (filter by `status`, e.g. needs_approval or failed), with what each waits on. (Wraps GET /api/v2/automations/actions.)

• act_on_publish_action

  [PUBLISHES to social accounts · `publish` scope] approve lets a rule's reshare / comment go out at its time; retry re-sends a failed one (same idempotency key); reject / cancel stop it. Confirm with the user before approving. Needs the…

• add_post_comments

  [PUBLISHES to social accounts · `publish` scope] Schedules comments on a post, sent once after it is live on that platform and its tokens resolve ({{postUrl}}, {{parentPostUrl:<post id>}}, {{youtubeUrl:<post id>}}), optionally at sendAt…

• list_post_comments

  [read-only] A post's comments-after-publish and reshares, with status (waiting, needs_approval, sent, failed) and the resolved text. (Wraps GET /api/v2/posts/{id}/comments.)

• list_frames

  [read-only] The brand's frames (borders, overlays, lower thirds, corner tags, quote-card frames, ribbons) plus the built-in flayr frames in the brand colors. Each has a `ref` to pass to apply_frame. (Wraps GET /api/v2/frames.)

• get_frame

  [read-only] One library frame with its sizes and content areas. (Wraps GET /api/v2/frames/{id}.)

• create_frame

  [writes flayr data · `write` scope] Copy a flayr frame into the brand library (`defaultKey`, optional colors/texts), or add uploaded PNG/SVG art (upload_media first; `variants` of storageIds, the content area is detected from…

• apply_frame

  [writes flayr data · `write` scope] Draws a frame over an image and returns a new image URL (the original is untouched). Use the URL in create_content, or pass contentId + platform so that post publishes the framed image on that platform…

• get_frame_settings

  [read-only] Which frame each platform's images get automatically when a post is published or scheduled. (Wraps GET /api/v2/frames/settings.)

• update_frame_settings

  [writes flayr data · `write` scope] Frame every image posted to a platform automatically (frameRef), or stop (frameRef null). Applies to posts published or scheduled from now on. Confirm with the user first. (Wraps POST…