Skip to content
ProtocolProbe
Explore

MCP servers › social.flayr › flayr

MCP server · registry snapshot 2026-10-30 · last tested 2026-10-30

flayr MCP server

Registry name social.flayr/flayr

by flayr.social · domain (the registry's namespace rule)Website ↗

Create, schedule and publish social posts to 13 platforms for your brands. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-30version 1.2.0streamable HTTP57 tools

Summary

social.flayr/flayr is a remote MCP server listed in the official MCP registry at version 1.2.0, under the namespace of the domain flayr.social. On 2026-10-30 ProtocolProbe connected to it in read-only mode and read its inventory: 57 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason

Operate this server? Correct a fact · README badge · Run the checks yourself

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Tools
57
Last tested
2026-10-30

Tool list size

34,089 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (57 tools). Counted with Anthropic's token counter on 2026-10-30, from the tool list we read on 2026-10-30. Median across 25,738 counted servers: 2,858 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-10-30 (flayr.social), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.2.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 27 tools whose name or declaration suggests they change data (upload_media, create_content, update_content, delete_content, publish and 22 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-30.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-30
Mode
read-only (no tool calls)
Latest version
1.2.0, published 2026-10-29 (registry, as of the 2026-10-30 snapshot)
First listed version
2026-10-29 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-10-30
Package and repository
checked 2026-10-30
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-10-29, listed on 2026-10-30 with version 1.2.0 (published 2026-10-29).

Source: the official MCP Registry list on 2026-10-29 and on 2026-10-30.

What it is

What does this server offer?

Observed inventory
57tools
0resources
0prompts

None of its 57 tools are described as changing anything. For 57 the reading was uncertain, so no mark is shown.

  • whoamion 177 other servers

    “[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 = a…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    Takes no inputs.

  • list_brandson 42 other servers

    “[read-only] Lists the brands this connection can file content into and publish through.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    Takes no inputs.

  • list_connected_accountson 2 other servers

    “[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…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • brandIdstring“An id from GET /api/v2/brands, or "personal".”
  • list_youtube_playlists

    “[read-only] Playlists of the YouTube channel(s) a brand publishes to.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • brandIdstring“An id from GET /api/v2/brands, or "personal".”
  • list_pinterest_boardson 1 other server

    “[read-only] Boards of the Pinterest account(s) a brand publishes to.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • brandIdstring“An id from GET /api/v2/brands, or "personal".”
  • upload_mediaon 12 other servers

    “[writes flayr data · `write` scope] Step 1 of attaching a LOCAL file (video or image) to a draft.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    Takes no inputs.

  • list_contenton 10 other servers

    “[read-only] Lists content items (drafts), newest first.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • limitinteger
    • includeArchivedboolean
    • brandIdstring“A brand id from GET /api/v2/brands.”
  • get_contenton 12 other servers

    “[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_h…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • create_contenton 2 other servers

    “[writes flayr data · `write` scope] Creates a DRAFT content item.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    15 inputs
    • textstring
    • copyFromContentIdstring“COPY TO BRAND (staff and the Agency plan): the id of an existing item (GET /api/v2/content) to copy into `brandId` as a new draft.”
    • platformsarray
    • contentTypestring
    • imageUrlstring
    • videoUrlstring
    • imageStorageIdstring
    • videoStorageIdstring
    • brandIdstring“An id from GET /api/v2/brands, or "personal".”
    • sourceLabelstring
    • youtubeobject“Stored on the draft and used when it is published (POST /api/v2/publish with contentId).”
    • referralFooterboolean“Caption watermark: appends "Posted with flayr.social — try it: flayr.social/r/<code>/<ch>" to each platform's text (<code> is your referral code — your custom …”
    • creditsarray“Creator credits for work this post uses.”
    • labelsarray“Normalized "key:value" labels (keys and values are lower-cased, spaces become "-").”
    • platformTextobject“Per-platform captions: platform id → the caption that platform gets instead of `text`, e.g.”
  • update_content

    “[writes flayr data · `write` scope] Edits a draft in place; only the fields you pass change.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    18 inputs, 1 required
    • idstringrequired
    • textstring
    • platformsarray
    • youtubeobject“Merged into the stored YouTube options.”
    • titlestring“Shorthand for youtube.title (the video title).”
    • creditsarray or null“Creator credits for work this post uses.”
    • platformTextobject or null“Per-platform captions: platform id → the caption that platform gets instead of `text`, e.g.”
    • labelsarray or null“Replaces the labels ([] or null clears).”
    • opusobject or null“Link this row to an Opus Clip clip (owner only; allowed on published rows) so an Opus project import skips it instead of creating a duplicate.”
    • videoWatermarkedobject or null“The item's own video already has the "Posted by flayr.social" watermark: publish it as-is.”
    • videoStorageIdstring“storageId from uploading to POST /api/v2/media/upload-url's uploadUrl.”
    • videoUrlstring“http(s) URL of the new video.”
    • imageStorageIdstring“Uploaded image storageId: the video's thumbnail, or on its own the post's single image.”
    • imageUrlstring“http(s) image URL: the video's thumbnail, or on its own the post's single image.”
    • imagesarray“Carousel image URLs.”
    • thumbnailStorageIdstring or null“Custom video thumbnail: an image storageId from POST /api/v2/media/upload-url.”
    • thumbnailUrlstring or null“Custom video thumbnail: an http(s) image URL.”
    • thumbnailFrameOffsetMsinteger“Use this frame of the video (ms from the start) as the cover.”
  • delete_contenton 3 other servers

    “[DESTRUCTIVE] DESTRUCTIVE: permanently deletes a content item from the library.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • 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…”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    5 inputs, 2 required
    • idstringrequired“The video to extend.”
    • segmentsarrayrequired“In playback order.”
    • transitionstring
    • crossfadeMsinteger“Crossfade overlap per join.”
    • audiostring
Show 45 more tools
  • get_job_statuson 32 other servers

    “[read-only] Status of an async job (combine_clips, or an API video generation): pending, processing, completed or failed.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • jobIdstringrequired
  • publishon 19 other servers

    “[PUBLISHES to social accounts · `publish` scope] PUBLISHES TO REAL SOCIAL ACCOUNTS.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    25 inputs, 1 required
    • contentstring“Post text.”
    • contentIdstring“An existing content item id (GET /api/v2/content/{id} access rules).”
    • platformsarrayrequired
    • imageUrlstring
    • videoUrlstring
    • brandIdstring“An id from GET /api/v2/brands, or "personal".”
    • scheduledAtstring“Must be in the future.”
    • mediaCampaignIdstring“Link to a media campaign; with a brand target it must belong to that brand.”
    • requiresApprovalboolean
    • aiGeneratedboolean“Label the post as AI-generated / synthetic media: YouTube containsSyntheticMedia, Instagram isAiGenerated, TikTok videoMadeWithAi, X madeWithAi, and the disclo…”
    • idempotencyKeystring“Unique per API key.”
    • allowDuplicateBookingboolean“A contentId that is already scheduled (a live booking still ahead) on one of these platforms is refused with 409 { code: "already_booked", bookedAt, bookedPlat…”
    • labelsarray“Labels for this post on top of the draft's own (the draft wins for type/cut/variant).”
    • youtubeobject“Overrides the content item's stored YouTube options field by field.”
    • facebookobject“Facebook post type.”
    • instagramobject“Instagram post type, same rules: "reel" (exactly one video — a single video is posted as a Reel), "story", or "feed".”
    • pinterestobject“FFE-428: Pinterest pin options for every Pinterest target.”
    • pollobject“A native poll.”
    • referralFooterboolean“Caption watermark: appends "Posted with flayr.social — try it: flayr.social/r/<code>/<ch>" to each platform's text (<code> is your referral code — your custom …”
    • reshareobject“Share/repost another post: a flayr post id (`postId`) or a pasted link (`url`).”
    • followUpCommentsarray“Comments after publish, sent once each (Idempotency-Key) after the post is live on that platform and its tokens resolve: {{postUrl}}, {{postUrl:<platform>}}, {…”
    • firstCommentobject“Explicit first comments per platform, posted right after the post goes out.”
    • autoFirstCommentboolean“When the target brand has "Auto first comment" on (dashboard: Brand → First comment), LinkedIn, Instagram, Facebook, Threads and YouTube targets that have no f…”
    • memoobject“"When it posts" memo: the people-steps after the post goes live (reply to a comment, share to a personal account, pin a link, add a first comment flayr can't).”
    • onPublishTasksarray“Shorthand for memo.tasks (appended after them).”
  • get_poston 66 other servers

    “[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 c…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired“The post: `convexPostId` from POST /api/v2/publish, or `posts[].id` from GET /api/v2/content/{id}.”
  • 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.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    6 inputs, 1 required
    • idstringrequired“The post: `convexPostId` from POST /api/v2/publish, or `posts[].id` from GET /api/v2/content/{id}.”
    • textstring“The caption (every platform without its own).”
    • platformTextobject or null“Per-platform captions, merged into the draft's: { "linkedin": "…" } sets one, null / "" clears it; null clears them all.”
    • firstCommentobject“The first comment the post publishes, per platform: a string sets it, null or "" removes it; platforms not named keep theirs.”
    • applyAutoFirstCommentboolean“Add the brand's auto first comment where the post has none.”
    • removePlatformsarray“Platform ids to drop from this booking (e.g.”
  • cancel_scheduled_poston 3 other servers

    “[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).”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    1 input, 1 required
    • idstringrequired“The post: `convexPostId` from POST /api/v2/publish, or `posts[].id` from GET /api/v2/content/{id}.”
  • list_reviewson 16 other servers

    “[read-only] Scheduled posts waiting for (or given) a human sign-off, oldest slot first.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • statusstring
    • brandIdstring
    • windowstring
  • decide_reviewon 3 other servers

    “[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 neve…”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    5 inputs, 2 required
    • idstringrequired“A convexPostId or a review id.”
    • decisionstringrequired
    • notestring
    • pastSlotstring or object“Only for a held post whose slot passed: "now", or { at: ISO-8601 future time }.”
    • collabSidestring“FFE-501 collab posts only: which brand this decision is for ("owner" = the shared character's brand, "grantee" = the brand that made the post).”
  • list_approvalson 5 other servers

    “[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 parke…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • statusstring
    • brandIdstring
  • decide_approvalon 2 other servers

    “[PUBLISHES to social accounts · `publish` scope] Same rules as the dashboard: only the assigned approver may decide.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    3 inputs, 2 required
    • idstringrequired“An approval id.”
    • decisionstringrequired
    • notestring
  • list_queueson 1 other server

    “[read-only] Posting (drip) queues of one brand.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • brandIdstring“Account-wide keys: "personal" or an id from GET /api/v2/brands (omitted → the brand last active in the dashboard).”
  • get_queueon 5 other servers

    “[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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • idstringrequired
    • brandIdstring“Account-wide keys: "personal" or an id from GET /api/v2/brands (omitted → the brand last active in the dashboard).”
  • create_queueon 2 other servers

    “[PUBLISHES to social accounts · `publish` scope] Creates a posting queue.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    9 inputs, 2 required
    • namestringrequired
    • platformsarrayrequired
    • cadenceHoursinteger“1, 2, 3, 4, 6, 8, 12, or whole days (24, 48, …, 720).”
    • timeOfDaystring“24-hour "HH:MM" local time.”
    • timezonestring“IANA timezone.”
    • lookaheadinteger“How many upcoming items are scheduled at the platform at once.”
    • startsAtstring“ISO 8601 with an offset (or Z).”
    • youtubeobject“Queue-wide YouTube defaults (a draft's own options win; titles are per item).”
    • brandIdstring
  • update_queue

    “[PUBLISHES to social accounts · `publish` scope] `status: "paused"` stops new bookings (already-booked posts stay booked); "active" resumes.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    9 inputs, 1 required
    • idstringrequired
    • brandIdstring
    • statusstring
    • namestring
    • platformsarray“Replaces the queue's platforms for items booked from now on.”
    • cadenceHoursinteger“1, 2, 3, 4, 6, 8, 12, or whole days (24, 48, …, 720).”
    • timeOfDaystring“24-hour "HH:MM" local time.”
    • lookaheadinteger
    • startsAtstring or null“ISO 8601 with an offset (or Z).”
  • delete_queue

    “[DESTRUCTIVE] DESTRUCTIVE: deletes the queue (its drafts stay in the library).”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    3 inputs, 1 required
    • idstringrequired
    • brandIdstring“Account-wide keys: "personal" or an id from GET /api/v2/brands (omitted → the brand last active in the dashboard).”
    • unscheduleboolean“true: delete every booked post at the platform first (the dashboard's "Unschedule"), then delete.”
  • 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.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    4 inputs, 1 required
    • idstringrequired
    • contentIdsarray
    • itemsarray
    • brandIdstring
  • 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 …”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    7 inputs, 2 required
    • idstringrequired
    • itemIdstringrequired
    • brandIdstring
    • actionstring
    • youtubeTitlestring or null“null or "" → back to the draft's stored title.”
    • platformsarray or null“This item's own platforms, used when it is booked; null → back to the queue's.”
    • positioninteger“0-based index among the waiting (queued) items.”
  • remove_queue_item

    “[DESTRUCTIVE] DESTRUCTIVE: removes an item (the draft stays in the library).”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    4 inputs, 2 required
    • idstringrequired
    • itemIdstringrequired
    • brandIdstring“Account-wide keys: "personal" or an id from GET /api/v2/brands (omitted → the brand last active in the dashboard).”
    • unscheduleboolean“true: delete the booked post at the platform first (the dashboard's "Unschedule"), then delete.”
  • reorder_queue_items

    “[PUBLISHES to social accounts · `publish` scope] Send every waiting (queued) item id exactly once, in the new order.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    3 inputs, 2 required
    • idstringrequired
    • itemIdsarrayrequired
    • brandIdstring
  • get_analyticson 32 other servers

    “[read-only] Engagement overview for the last 7, 30 or 90 days.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • rangestring
  • 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>, …”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    12 inputs
    • formatstring“csv = the result as a spreadsheet-safe CSV attachment (UTF-8 BOM, CRLF, cells starting with = + - @ are prefixed with ').”
    • metricstring
    • aggregationstring“Default median; pooled for the rates engagementRate, ctr and completionRate.”
    • breakdownarray“Up to 2 of: platform, brand, campaign, experiment, arm, weekday, hour, postType, or label:<key> (e.g.”
    • windowstring“Snapshot age: the metric as it stood 48h / 7d / 30d after publish, or the latest refresh.”
    • intervalstring“Adds a time series bucketed by publish date.”
    • filtersobject
    • dateFromstring“ISO date or epoch ms (publish time).”
    • dateTostring“ISO date or epoch ms.”
    • tzOffsetMinutesinteger“Offset from UTC for weekday / hour / day buckets (e.g.”
    • brandIdstring“A brand id, or "all" (default: every profile you can see).”
    • formulaobject“Optional (needs the Advanced insights feature): combine up to three series.”
  • compare_labels

    “[read-only] Splits every labelled post by the values of one label key (e.g.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    5 inputs
    • keystring
    • brandIdstring“A brand id, or "all" (default: every profile you can see).”
    • windowstring
    • metricstring“Which metric "leading" ranks by.”
    • includestring
  • list_experimentson 7 other servers

    “[read-only] A/B experiments.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • brandIdstring“A brand id, or "all" (default: every profile you can see).”
    • allBrandsboolean“true: every brand of the organizations you own or administer, plus your personal brands.”
  • get_experimenton 6 other servers

    “[read-only] One experiment: hypothesis, variants, compareKey, window and status.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • create_experimenton 5 other servers

    “[writes flayr data · `write` scope] Creates an A/B experiment.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    10 inputs, 1 required
    • namestringrequired
    • hypothesisstring
    • compareKeystring
    • variantsarray
    • startAtstring or null
    • endAtstring or null
    • statusstring
    • primaryMetricstring
    • notesstring
    • brandIdstring“A brand id, or "personal" (default).”
  • update_experimenton 4 other servers

    “[writes flayr data · `write` scope] Changes an experiment's fields (e.g.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    10 inputs, 1 required
    • idstringrequired
    • namestring
    • hypothesisstring
    • compareKeystring
    • variantsarray
    • startAtstring or null
    • endAtstring or null
    • statusstring
    • primaryMetricstring
    • notesstring
  • delete_experimenton 1 other server

    “[DESTRUCTIVE] DESTRUCTIVE: deletes the experiment record (content keeps its labels).”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • get_experiment_resultson 1 other server

    “[read-only] The experiment's posts split by its compareKey, with the leading variant by its primary metric and n per arm.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs, 1 required
    • idstringrequired
    • windowstring
    • includestring
  • list_text_templates

    “[read-only] Reusable text shapes per brand: sections, length targets, hook patterns, CTA slots and guardrails.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • brandIdstring“A brand id (GET /api/v2/brands), "personal", or "all" (default: everything the key owner can see).”
    • includeArchivedboolean
  • get_text_template

    “[read-only] One format (text template) with its full structure and example.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • create_text_template

    “[writes flayr data · `write` scope] Creates a reusable format (text template) in a brand.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    14 inputs, 3 required
    • namestringrequired
    • formatstringrequired
    • platformstring or null“e.g.”
    • useForstring or null“One line: when to pick this format.”
    • lengthobjectrequired
    • sectionsarray“In order.”
    • hookPatternsarray“"[slot]" placeholders are kept as written.”
    • ctaSlotsarray
    • guardrailsarray
    • maxHashtagsinteger or null
    • defaultLabelsarray“"key:value" labels every draft started from this format gets (plus the format's own `label`).”
    • examplestring or null
    • sourcestring or null“Where the shape came from, e.g.”
    • brandIdstring
  • update_text_template

    “[writes flayr data · `write` scope] Changes a format; only the fields you pass change.”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    15 inputs, 1 required
    • idstringrequired
    • namestring
    • formatstring
    • platformstring or null“e.g.”
    • useForstring or null“One line: when to pick this format.”
    • lengthobject
    • sectionsarray“In order.”
    • hookPatternsarray“"[slot]" placeholders are kept as written.”
    • ctaSlotsarray
    • guardrailsarray
    • maxHashtagsinteger or null
    • defaultLabelsarray“"key:value" labels every draft started from this format gets (plus the format's own `label`).”
    • examplestring or null
    • sourcestring or null“Where the shape came from, e.g.”
    • archivedboolean
  • delete_text_template

    “[DESTRUCTIVE] DESTRUCTIVE: deletes a format (drafts started from it keep their text).”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • list_attribution_rules

    “[read-only] The brand's "posts like this must carry a credit" rules and its mode (flag / push_down).”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • brandIdstring“Account-wide keys: "personal" or an id from GET /api/v2/brands (omitted → the brand last active in the dashboard).”
  • 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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input
    • brandIdstring“Account-wide keys: "personal" or an id from GET /api/v2/brands (omitted → the brand last active in the dashboard).”
  • create_share_rule

    “[PUBLISHES to social accounts · `publish` scope] Creates a rule that reshares (or comments on) every new post of the source accounts.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    10 inputs, 2 required
    • namestringrequired
    • enabledboolean
    • kindstring“`reshare`: share the post to `targets`.”
    • sourceAccountIdsarrayrequired“Fires when a post goes live through any of these connected accounts.”
    • sourceLabelstring or null“Only posts carrying this label.”
    • targetsarray
    • templatestring“The reshare commentary or comment text.”
    • delayMinutesinteger
    • approvalstring“`needs_approval` (default): each fire waits for a person (POST …/actions/{id} `approve`).”
    • brandIdstring
  • list_publish_actions

    “[read-only] Pending, sent and failed comments-after-publish and reshares of the brand (filter by `status`, e.g.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • brandIdstring“Account-wide keys: "personal" or an id from GET /api/v2/brands (omitted → the brand last active in the dashboard).”
    • statusstring
  • 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.”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    2 inputs, 2 required
    • idstringrequired
    • opstringrequired
  • 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>}}, {{youtubeU…”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    2 inputs, 2 required
    • idstringrequired
    • commentsarrayrequired
  • list_post_comments

    “[read-only] A post's comments-after-publish and reshares, with status (waiting, needs_approval, sent, failed) and the resolved text.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • list_frameson 2 other servers

    “[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.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • kindstring
    • aspectstring
    • includeArchivedboolean
  • get_frameon 4 other servers

    “[read-only] One library frame with its sizes and content areas.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • idstringrequired
  • create_frameon 8 other servers

    “[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 con…”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    8 inputs
    • defaultKeystring“A defaults[].ref without "default:".”
    • paletteOverrideobject“Colors that win over the brand kit.”
    • textsobject“Texts some frames print (ribbon/tag label, lower-third title/subtitle).”
    • namestring
    • kindstring“Default: guessed from the name.”
    • tagsarray
    • variantsarray“One per aspect ratio.”
    • rightsstring“Who holds the rights to the art.”
  • apply_frame

    “[writes flayr data · `write` scope] Draws a frame over an image and returns a new image URL (the original is untouched).”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    12 inputs, 2 required
    • sourceUrlstringrequired“https image URL (flayr/Convex storage or a stock host).”
    • frameRefstringrequired“`default:<key>` or `brand:<id>` from GET /api/v2/frames.”
    • aspectstring“Default: nearest to the source image.”
    • fitstring
    • zoomnumber
    • offsetXnumber
    • offsetYnumber
    • paletteOverrideobject“Colors that win over the brand kit.”
    • textsobject“Texts some frames print (ribbon/tag label, lower-third title/subtitle).”
    • platformstring“Platform this framed image is for ("all" by default).”
    • slideIndexinteger“Image position in the post.”
    • contentIdstring“A content id: its publish swaps this framed image in for `platform`.”
  • get_frame_settings

    “[read-only] Which frame each platform's images get automatically when a post is published or scheduled.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    Takes no inputs.

  • update_frame_settings

    “[writes flayr data · `write` scope] Frame every image posted to a platform automatically (frameRef), or stop (frameRef null).”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    3 inputs, 2 required
    • platformstringrequired
    • frameRefstring or nullrequired
    • aspectstring

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-30.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
51% of 259
Tools with a description
100% of 57
Typical description length
347 characters

The tool set

Counted from the listing

Tools
57
Size of the list
about 22,923 tokens for an agent to load (characters ÷ 4)
Naming
55 of 57 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 57 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-30 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://flayr.social/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "flayr": {
      "url": "https://flayr.social/api/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "flayr": {
      "type": "http",
      "url": "https://flayr.social/api/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"flayr","type":"http","url":"https://flayr.social/api/mcp"}'
Claude Code
claude mcp add --transport http flayr https://flayr.social/api/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "flayr": {
      "type": "streamableHttp",
      "url": "https://flayr.social/api/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "flayr": {
      "httpUrl": "https://flayr.social/api/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.flayr]
url = "https://flayr.social/api/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "flayr": {
      "url": "https://flayr.social/api/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://flayr.social/api/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint flayr.social/api/mcpSession openedmatchesour test · 2026-10-30
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-30

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-30. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about social.flayr/flayr

Answered from the data above

Who publishes social.flayr/flayr?

The registry ties the namespace social.flayr to the domain flayr.social; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.

Does social.flayr/flayr need an API key or sign-in?

It opened a session without any credential on 2026-10-30. The registry entry declares no required credential; no declaration is not a guarantee.

Has social.flayr/flayr been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-30
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3
  • 1Inventory
    tool-list    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-30, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,452 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 57 tools, 0 resources, 0 prompts.
  4. 7,110 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added in a later update
listed 2026-10-30; not classified yet
Pricing modelAI-classified
pending: added in a later update
the website is not read yet
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
remote (hosted by the publisher)
registry · 2026-10-30
MCP capability
tools
our test · 2026-10-30
Transport
streamable HTTP
registry · 2026-10-30
Required credentials
none declared
registry · 2026-10-30 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-30
Lifecycle status
active
registry · 2026-10-30
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-10-30

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “social.flayr/flayr: MCP server record.” Data checked 2026-10-30. https://protocolprobe.com/mcp/servers/social.flayr/flayr

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/social.flayr/flayr)](https://protocolprobe.com/mcp/servers/social.flayr/flayr)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology