Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

CueFrame

REMOTE · API.CUEFRAME.AI

Turn footage into finished video: reframing, captions behind the subject, motion graphics, renders.

Available components

+3 this week 86 Trust /100

Last scanned (13 hours ago)

Scores higher than 93% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability100
Schema Quality & AI Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 22516 tokens (~210/item across 107 items; 107 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 77% of tool parameters carry a description.Partial
  • Structured output schemas are declared (70% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 108 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 0
    • Tool “apply_composition” rewrote its description, which is the text the model reads security
    • Tool coverage: 82% → 77% ▼ functional
    • Server version: 0.13.1 → 0.13.4-ea20261031.1 functional
    • New tool “acquire_registry_item” functional
    • New tool “create_template_package_upload” functional
    • New tool “describe_tool_input” functional
    • New tool “export_template_package” functional
    • New tool “get_registry_acquisition” functional
    • New tool “get_registry_item” functional
    • New tool “get_template_job” functional
    • New tool “get_template_package_download” functional
    • New tool “import_template_package” functional
    • New tool “refresh_registry_snapshot” functional
    • New tool “search_registry_items” functional
  • 30 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 29 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_composition” rewrote its description, which is the text the model reads security
    • Tool “preview_frame” rewrote its description, which is the text the model reads security
    • Tool “apply_composition” now declares an output schema ▲ functional
    • Tool “get_composition” now declares an output schema ▲ functional
    • New prompt “cueframe-reference-video” functional
    • Server version: 0.12.0 → 0.13.1 functional
    • New tool “compare_frames” functional
    • “apply_composition” added an optional parameter “response” cosmetic
    • “get_composition” added an optional parameter “clipIds” cosmetic
    • “get_composition” added an optional parameter “dependencyKeys” cosmetic
    • “get_composition” added an optional parameter “response” cosmetic
    • “wait_job” added an optional parameter “imageIndices” cosmetic
  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://api.cueframe.ai/v1/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.cueframe.ai CN=WE1,O=Google Trust Services,C=US 10 Oct 2026 8 Jan 2027 ECDSA 256 ECDSA-SHA256 45851ae969a634b4137a79e2bed24c83
SANs: api.cueframe.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.cueframe.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814, 3799 8, 8 Verified
cueframe.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://api.cueframe.ai/.well-known/oauth-protected-resource"

Bearer resource_metadata="https://api.cueframe.ai/.well-known/oauth-protected-resource"

Protected resource metadata

Document https://api.cueframe.ai/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://api.cueframe.ai/v1/mcp
Authorisation server https://api.cueframe.ai

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.cueframe.ai/v1/mcp Verified 200
http (plaintext) http://api.cueframe.ai/v1/mcp HTTPS enforced 301 https://api.cueframe.ai/v1/mcp
MCP tools · 107 exposed · ~18,710 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
repin_component ~239

Move clips stored in a retired form to their native (version 4) successors: a clip pinning a retired TSX (version 3) component, or one stored before execution pins (`needsUpgrade` kind `unpinned-component`), moves to the `successorSourceVersionId` that get_composition's `needsUpgrade` (or a `component_source_retired` refusal) names. Pass projectId and, in `body`, optional `clip_ids` (omit them to move every clip that has a successor) and `composition_id` (the active composition when omitted). Saved inputs are kept. The answer lists `moved` and `withoutSuccessor`; rebuild the latter as native components (create_component, then apply_composition at the same timing and placement). A retired clip with no successor must be rebuilt or removed in the same write that upgrades the others: a write never leaves one in place.

NameTypeReqDescription
bodyobjectyes–
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
projectIdstringyesprojectId (path).
NameTypeReqDescription
etagstring|null––
inputsRefusedarray–Clips whose successor refuses their stored inputs (its input schema), each with why: fix the inputs by rebuilding the clip, or remove it.
movedarray––
withoutSuccessorarray–Clips in a retired form no curated release recorded: rebuild them as native components, or remove them, in the same edit that upgrades the others.

No examples provided.

resolve_builtin_component ~107

Resolve a selected builtin component-library card using its exact collection, id and revision. Returns the canonical pinned document and source snapshots for a preset or recipe, or the exact source for a definition. Preserve documentSha256 and all identities; a missing revision refuses without falling back to another version or scope. Resolve before apply_template; do not invent wrapper source or reconstruct a package from a thumbnail.

NameTypeReqDescription
collectionstringyes–
idstringyes–
revisionstringyes–
NameTypeReqDescription
cardobject––
documentobject––
documentSha256string––
documentTextstring––
presetobject––
previewDelivery–yes–
previewMediaobject––
sourceobject––
sourcesarray––

No examples provided.

resume ~272

Answer the checkpoint packet wait_job reported as awaiting_input (its {checkpointId} — read the packet FIRST with get_checkpoint and relay the stills + money triple to your human). ONE `body.decision` per gate: 'approve' (proceed; comments allowed — they record as taste without gating), 'revise' (the director revises per your `body.comments` [{anchor: {beatId}|{timecodeMs}, verdict: 'approve'|'revise'|'lock', note}] and/or `body.edits`, then RE-PRESENTS this same gate as a new packet — in-job, no new charge; the brief quote states the included revision cycles, beyond them revise is refused 402), or 'abandon' (end the run — the only terminal refusal). 'lock' freezes an element contractually: the director touching it surfaces as a lock_violation verdict on the next packet. On approve/revise the Director rehydrates its warm box and continues; then wait_job again.

NameTypeReqDescription
bodyobjectyesPOST /checkpoints/:id/resume body — the A1 review grammar.
checkpointIdstringyescheckpointId (path).
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
NameTypeReqDescription
okboolean––

No examples provided.

retry_render ~235

Re-render an existing render job's FROZEN composition snapshot — it inherits that job's exact composition/intent/priority and queues a fresh renderJob; it does NOT re-read the project's current composition. So it only helps a TRANSIENT failure (the failed render's `retryable:true` / `category:"transient"` — a flaky pipeline/infra fault): re-attempting the same snapshot may succeed. For a DETERMINISTIC failure (`retryable:false` / `category:"authoring"` — a bad param, an unresolvable media/brand ref), retry_render reproduces the SAME failure: FIX the composition first via apply_composition, then create_render (a retry alone is futile). Check `retryable` on getRender / wait_job to pick the path. Returns the new render; then wait_job(kind="render", id=<new id>).

NameTypeReqDescription
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
projectIdstringyesprojectId (path).
renderIdstringyesrenderId (path).
NameTypeReqDescription
category––Failure taxonomy when status is `error`; null otherwise. `authoring` = deterministic defect in YOUR composition/request — fix it, retrying is futile; `transient` = temporary pipeline/infra failure —…
completedAtstring|null–ISO-8601 instant the render reached its terminal status (complete, error or cancelled); null while it runs. Pair with createdAt for the wall time.
compositionIdstring|null–The composition this render froze at create time (the project's active one, or the compositionId the request named). Null on renders minted before this was recorded.
createdAtstring––
engine––The render engine the row was minted for. Null on rows minted before the engine was recorded.
errorstring|null–Human-readable failure message. Pair with `errorCode` for a stable, machine-readable code an agent runner can branch on.
errorCodestring|null–Stable, machine-readable error code (e.g. `render_pipeline_unavailable`, `render_route_missing`, `render_pipeline_failed`). Null when status is not `error` or unavailable for an older render.
errorDetails––Structured failure context — `{ targetUrl?, upstreamStatus?, upstreamCode?, attemptedAt? }`. Surfaced so agent runners can distinguish operator-config issues from upstream-down vs route-missing witho…
format––The resolved output format the render was encoded at (aspectRatio, fps, resolution): the frozen composition's, after any create-time scale override. Null on legacy rows.
idstring––
listUsdnumber–A2 money stamp: the metered event's LIST price (USD), stamped at the success terminal (exports for deliverable renders, compose_capture for A8 previews). A plan allowance may zero the actual invoice…
outputDurationSecnumber|null–The output's length in seconds (the composition timeline's, or the preview window's), as billed. Null on legacy rows.
outputExpiresAtstring|null––
outputUrlstring|null––
preview––The scoped preview window when this is a preview_clip render; null for a full deliverable.
progressobject–Non-terminal render progress; phase is one of the worker's emitted stages.
retryableboolean|null–Whether re-attempting the SAME render can succeed (status `error`); null otherwise. true → call retry_render. false → deterministic (category authoring/internal); fix the composition first — retry_re…
statusstring––
updatedAtstring–ISO-8601 timestamp of the render's most recent progress update. Compute staleness = now − updatedAt to distinguish a wedged render from a slow one and decide whether to wait, cancel, or retry.
warningsarray–Non-fatal advisories surfaced at render-CREATE (omitted when none, and on GET — create-time only).

No examples provided.

score_composition ~156

Queue the durable server-side judge — it snapshots the exact authored target, samples eval beats, captures frames asynchronously, and grades editorial/spatial/brand/caption. Then wait_job(kind="verify", id=jobId) for per-criterion scores, weighted composite, worst-first critique, and checkpointId. `body.composition` is optional (absent ⇒ ACTIVE). Fix the lowest criterion via apply_composition and re-score. Idempotent per immutable snapshot; compose_verify bills only on the guarded success terminal.

NameTypeReqDescription
bodyobjectyes–
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
projectIdstringyesprojectId (path).
NameTypeReqDescription
jobIdstring–Poll GET /v1/jobs/{jobId} / wait_job until terminal.
jobKeystring–Deterministic identity of the work (content hash of every input the result depends on). Re-enqueueing the same key returns the same job while it runs; a failed key revives as a fresh attempt.
kindstring–Job family, e.g. `verify` | `preview` | `brand_kit_extract`.
statusstring–running on a fresh/deduped enqueue; succeeded when an identical request already completed. Cancelled is part of the shared status vocabulary; identical cancelled work revives to running.

No examples provided.

search_fonts ~165

Search web font families by name/style — returns family names to use in composition/component params. Pass query (+ optional perPage ≤50). Read-only + free; surfaces the Google Fonts catalog (family + category + variants + css2 stylesheet URL). IMPORTANT: this searches the GOOGLE catalog, not what the render can actually draw. Only the faces vendored into the render page are guaranteed to rasterize; naming any other family gets you the generic fallback (Liberation Sans) with no error. Call list_render_fonts for the set you may actually choose from, WITH the admitted weights per family — treat that, not this catalog, as the list. An empty result set here means no match, or the upstream catalog was unavailable.

NameTypeReqDescription
bodyobjectyesPOST /fonts/search body.
NameTypeReqDescription
resultsarray––

No examples provided.

search_registry_items ~213

Discover external registry source candidates through the maintained pinned client. Omit every snapshot field to use the current organization snapshot, or provide registryOrigin, sourceCommit, inventorySha256 and cliArtifactSha256 together. Preserve the exact returned snapshot, item manifest digest, source requirements and unverified upstream preview provenance. Results may be partial; zero compatible candidates in a shortlist does not prove catalog-wide absence. itemType:example lists examples in inventory order; query/tag ranking for examples is unsupported. These are external candidates, not insertable CueFrame cards or rendered fidelity evidence. If no current snapshot exists, explicitly refresh with an observed null snapshot and revision; do not fabricate pins.

NameTypeReqDescription
cliArtifactSha256string––
cursorstring––
inventorySha256string––
itemTypestring––
limitinteger––
querystring––
registryOriginstring––
sourceCommitstring––
tagstring––
NameTypeReqDescription
completenessstring––
itemsarray––
nextCursorstring––
searchTierstring––
snapshotobject––
snapshotRevisioninteger––
staleboolean––
totalItems–––
warningsarray––

No examples provided.

search_resources ~235

Search licensed stock media to compose with across video, photo, sound effects, and GIFs. Pass query for ONE search, or queries[] (≤10) to run them all in a SINGLE call — strongly prefer the batch when you know several things you need. A batch returns results[], one per query in order, each with its own candidates; a query that fails carries an error and never discards the others. Optional kind [default video], provider pin, and limit ≤50 apply to every query in the batch. Returns ranked candidates, each with an opaque candidateId + attribution (author, assetUrl) + license, and a preview URL in the text. FREE + rate-limited + cached — reach for this before generate_media when real footage beats synthesis. TO SEE the candidates rather than read about them, pass limit ≥2: thumbnails/audio are attached only when you asked for options to compare. Import a chosen candidate into a project with import_resource. Candidate handles expire; re-search to refresh one.

NameTypeReqDescription
bodyobjectyesPOST /resources/search body — one `query`, or a batch of `queries[]`.
NameTypeReqDescription
candidatesarray––
kindstring––
providerstring––
resultsarray––

No examples provided.

select_candidate ~220

Select one candidate from a finished compose/consult ensemble as the project's saved composition (whole-candidate replace). Body REQUIRES both fields: { candidateIndex, selectStrategy: "agent-authoritative" } — candidateIndex from wait_job(kind="consult") proposals (mode=amend) or the compose winner report; selectStrategy is required and API keys must use 'agent-authoritative' (editor-merge/editor-replace need an editor-session token and 403 on an API key). agent-authoritative replaces the saved composition unconditionally and ignores ifMatch, so read get_composition first and adopt only when no edit made since the consult or compose must survive. After selecting, render with create_render.

NameTypeReqDescription
bodyobjectyesPOST /projects/:id/compose/jobs/:jobId/select body.
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
composeJobIdstringyescomposeJobId (path).
projectIdstringyesprojectId (path).
NameTypeReqDescription
mergeResultobject––
newCompositionEtagstring––

No examples provided.

start_template ~125

Create a new project from a catalog or org template. The server prepares media and verified mattes before the project is ready. Pass the returned jobId to wait_job(kind="template").

NameTypeReqDescription
brandKitIdstring––
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
idempotencyKeystring––
mediaobject––
presetstring––
projectNamestringyes–
templatestringyes–
valuesobject––

No output schema declared.

No examples provided.

suggest_briefs ~186

Run AI clip-suggestion analysis on a long-form media item — the CLIPPING path (find the best short-form moments). Returns { status, alreadyRunning? }; then wait_job(kind="suggestions", id=mediaItemId) — its terminal lists each suggestion WITH its briefId. When the media belongs to a PROJECT, each finalized suggestion is promoted to a kind-'clip' BRIEF (its window pinned as a beat) — list_briefs {kind:"clip"} shows them and compose({ briefId }) runs the flagship path from one. Project-less media: pass the suggestion id to compose({ suggestionId }) directly. Clipping is a vertical, NOT the general path.

NameTypeReqDescription
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
mediaItemIdstringyesmediaItemId (path).
NameTypeReqDescription
alreadyRunningboolean––
statusstring––

No examples provided.

update_brief ~100

Edit a brief (partial). REFUSED with 409 while an ACTIVE compose job references it — finish, resume, or abandon the job first (the Director never has its input edited mid-run). Edits apply to the NEXT compose.

NameTypeReqDescription
bodyobjectyes–
briefIdstringyesbriefId (path).
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
NameTypeReqDescription
audiencestring––
audioobject––
beatsarray––
captionstring––
captionsobject––
createdAtnumber––
ctastring––
durationSecnumber–Target output duration. HONOR-OR-REFUSE: compose validates it against the beat-source window (±1.5s) and refuses a brief it cannot honor.
exclusionsarray––
formatobject––
gatesobject––
goalstring–What the video must accomplish.
hookstring––
idstring––
kindstring–authored = create_brief; clip = minted by suggest_briefs from an AI clip suggestion.
localestring–Output language (BCP-47 tag, e.g. 'es-419'): ALL on-screen copy + captions.
motionStyleobject––
mustIncludesarray––
namestring––
platformstring––
projectIdstring––
quoteobject––
referencesarray––
seededGraphicsarray–Client-authored graphic clips the Director must carry VERBATIM: seeded into the design loop's base composition as LOCKED clips (never re-authored, never discarded).
sourceSuggestionIdstring–kind:'clip' provenance — the suggestion this Brief was minted from.
tonestring––
updatedAtnumber––

No examples provided.

update_component ~388

Update an authored component's complete version-4 source/metadata IN PLACE (same id) — the correct verb for the author→preview→fix loop (preview_component returns the admission or runtime error; fix the template here and re-preview, instead of creating a new component each iteration). Pass componentId + the changed fields as `body`. Same source contract as create_component: {version:4, componentId, template, manifest, definition}, admitted before the write; the template finds its root with document.getElementById('root'), and declared slots arrive in the scene's `assets`, never params. PLACED CLIPS: every placed clip renders the exact version it pins, so an update moves placed clips ONLY when you name a project — put `projectId` (and optionally `compositionId`; default the project's active composition) in `body`, and that composition's placements move to the new version in the same write. The answer carries `repinned` (what moved) and `placementsPinnedToPrevious` (placements across the org still rendering the previous version). Without `projectId` nothing placed moves: previews and renders of an existing clip keep the old version. For one placement, register the source WITHOUT projectId, read its immutable sourceVersionId, then use apply_composition clip.update to change only the selected clip source and exact pin under observed concurrency expectations. Explicit-project update_component admits and repins all matching placements in that composition; use it only when that broader edit is requested.

NameTypeReqDescription
bodyobjectyesPUT /components/:id body: every writable field, all optional; an omitted field is carried forward. Org/user are server-resolved; never accepted from the body.
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
componentIdstringyescomponentId (path).
NameTypeReqDescription
avoidWitharray–Authoring guidance: ids of primitives that CONFLICT with this one — do not place together.
brandBindingsarray–Params that can follow the project brand kit. Each {param, brandToken} says: set `param` to `brandToken` (a `$brand:` ref, e.g. '$brand:colors.accent') to track the brand instead of a literal. See th…
categorystring––
descriptionstring––
durationInFramesnumber––
ejectedFromstring––
examplesarray–Usage examples, as authored. A built-in primitive projects {name, mood?, params?, description?}; an authored component's examples are whatever it wrote, which is why the item is open. One shape for b…
fixedCopyarray–On-screen strings this primitive BAKES — the read-side counterpart to propSchema. These literals render REGARDLESS of params (no param can change them); fork the source via get_component_source to ed…
formatobject––
idstring–The entry's id: a `primitiveId` for a built-in, a `componentId` for an installed component.
intentstring–Selection signal: a verb naming what this primitive accomplishes (e.g. 'product-trailer'). Match it to the beat you are authoring.
kindstring–RENDER kind (component | transition | scene). NOT the ClipSource variant — see `placement` for how to author it on the timeline.
manifest–––
moodarray–Vibe/tone tags (e.g. 'cinematic', 'minimal'). Filter to match the edit's mood.
namestring––
originstring––
pairsWitharray–Authoring guidance: ids of primitives that COMPOSE well with this one in the same edit.
placementobject––
placementsPinnedToPreviousinteger–Placements across the org that still pin the previous version and will keep rendering it. Name `projectId` (and `compositionId`) on the update to move a composition's placements with it.
propDefaultsobject––
propSchemaobject––
repinnedobject–Present when the update named `projectId`: the composition whose placements moved to the new version.
sourcestring–'default' = built-in primitive (place by primitiveId); 'installed' = org-authored component (place by componentId).
subtextParamstring|null–The param field for secondary text (subtitle/byline); null = none.
tagsarray–Free-text search keywords.
textParamstring|null–The param field that carries this primitive's primary text; null = no single text slot.
tierstring–Quality/applicability RANKING (a preference, not a flag). Prefer 'recommended'; reach for 'niche' only when its specific use-case is exactly the beat.
tokensobject––
useCasearray–The edit ROLE(s) this primitive fills — the dimension to filter by for a beat (e.g. 'intro', 'title-over-footage', 'grade').
useWhenstring–When to use this — AND when not to. The negative guidance is load-bearing; read it before picking.
versionstring–The ENTRY's version: a semver string ('0.0.0' until an authored component is versioned). Distinct from `manifest.version`, which is the runtime contract version (4 native, 2 retired TSX).
warningsarray–Non-blocking save-time advisories — the create/update SUCCEEDED. Currently: a `fontFamily` string literal referencing a NON-vendored font (a bare CSS generic like 'serif', or an unknown named family…

No examples provided.

update_project ~113

Update a project's mutable fields (e.g. name, format, brandKitId). Pass projectId + the changed fields as `body`. Setting brandKitId binds/changes the project brand kit so every render of this project themes from it. Returns the updated ProjectResponse.

NameTypeReqDescription
bodyobjectyesPATCH /projects/:id body.
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
projectIdstringyesprojectId (path).
NameTypeReqDescription
activeCompositionIdstring|null––
brandKitIdstring|null––
compositionobject–Summary of a project's stored composition.
createdAtstring––
descriptionstring|null––
format–––
idstring––
lastRender––Most recent render for a project, if any.
namestring––
webUrlstring|null–A browser URL that opens THIS project, or null when CueFrame exposes no web view for a project. Null today: the console serves account surfaces (keys, usage, billing) and has no per-project page, so…

No examples provided.

update_webhook ~89

Update a webhook subscription (its url or event list). Pass webhookId + changed fields as `body`. The signing secret is NOT rotated here.

NameTypeReqDescription
bodyobjectyesPATCH /webhooks/:id body.
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
webhookIdstringyeswebhookId (path).
NameTypeReqDescription
consecutiveFailuresinteger––
createdAtstring––
enabledboolean––
eventsarray––
idstring––
lastDeliveredAtstring|null––
lastFailedAtstring|null––
settleMsinteger––
urlstring––
verificationStatusstring–pending = callback URL has not echoed the ownership challenge (receives no events); verified = ownership proven.

No examples provided.

validate_composition ~309

Dry-run a full Composition object against the SAME pure, DB-free authoring guards saveComposition enforces, WITHOUT persisting it (no project needed). Checks: wire shape (Zod), primitive membership (unknown_primitive / custom_missing_sourcecode), required-param shape (invalid_primitive_params), clip↔track family (clip_source_track_mismatch), and reframe coverage (reframe_coverage_gap). Always returns ONE shape — 200 { valid, errors, quote } — for BOTH malformed wire shapes and deep-invariant failures (so branch on `valid`, not on HTTP status); errors[] lists every problem at once as a sanitized envelope { code, stage, category, retryable, message, fix } you can fix before composing/rendering. The `quote` triple states the render price to finish from a valid composition — relay it to your human BEFORE create_render. `valid:true` means save-safe EXCEPT for the three genuinely DB-bound checks that can only run at save/render, because this tool takes no project: trim-bounds (needs the media duration), image/asset-on-a-video-track (needs the media kind), and componentId resolution (needs the installed components of YOUR org — a `{kind:'component', componentId, props}` clip naming a component you have not created, or naming a CATALOG PRIMITIVE, passes here and is refused at save with `component_source_unavailable`). Pass the Composition as `body`.

NameTypeReqDescription
bodyobjectyes–
NameTypeReqDescription
advisoriesarray–Deterministic, render-free QUALITY floors (the SAME named defects the Director's in-loop verify and score_composition surface: static-hold, caption-spine, sfx-density, sfx-speech-collision, bed-cover…
contractstring–The contract this verdict was computed against (the kernel version the deployment runs). If it differs between two calls, the validator changed, not your composition.
errorsarray––
quoteobject–The A2 money triple for the commodity lane: validate is free; estimatedJourneyTotalUsd is the render price to finish from a valid composition — relay it BEFORE create_render.
validboolean––
warningsarray–Non-blocking render-fidelity warnings detected before enqueue, including unavailable font families.

No examples provided.

verify_webhook ~157

Re-run ownership verification on a PENDING webhook — one whose endpoint did not echo the challenge at create time (check its verification.reason: token_not_echoed / non_2xx_<code> / unreachable / ssrf_blocked). After you fix the receiver to reply 2xx echoing data.token, call this to re-send the signed webhook.verify challenge and flip it active IN PLACE (id + secret preserved — no delete/recreate). Returns { id, status:"active"|"pending", verification? }. An already-active webhook returns active unchanged.

NameTypeReqDescription
commandId––Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
webhookIdstringyeswebhookId (path).
NameTypeReqDescription
idstring––
statusstring–active = ownership verified + receiving events; pending = challenge not echoed.
verificationobject–Present only when the re-challenge did not verify; `reason` names why (see WebhookCreateResponse.verification).

No examples provided.

wait_job ~243

Wait for a long-running job and return the resolved result — a bounded long-poll. Includes template preparation (kind="template", id=jobId), media import, render, compose, consult, suggestions and preview. If still running, call wait_job again with the same arguments; work continues server-side.

NameTypeReqDescription
idstringyeskind="media": mediaItemId returned by import/generate/finalize/import_resource. kind="render": renderId. kind="compose": composeJobId. kind="consult": consultJobId. kind="suggestions": mediaItemId. G…
imageIndices––Read these 1–4 original zero-based image artifact indices from this completed job, in this order. Does not render again. Same arguments repeat the same selection; omit for the first four.
kindstringyesWhat to wait on, including template preparation (kind="template").
projectId––Required when kind="render", "compose", or "consult".
timeoutMs––Maximum wait in ms (default 30 min for render/compose, 5 min for suggestions).

No output schema declared.

No examples provided.

Install

How do I install the CueFrame MCP server?

CueFrame is a hosted endpoint at https://api.cueframe.ai/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.cueframe.ai

# add to Claude Code
claude mcp add --transport http ai-cueframe-cueframe 'https://api.cueframe.ai/v1/mcp'
Common questions

What is the CueFrame MCP server?

CueFrame is an MCP server listed in the public MCP registry as ai.cueframe/cueframe. Turn footage into finished video: reframing, captions behind the subject, motion graphics, renders. This page covers its hosted endpoint (https://api.cueframe.ai/v1/mcp).

Is the CueFrame MCP server safe to use?

CueFrame scores 86 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the CueFrame MCP server expose?

CueFrame exposes 107 tools: search_registry_items, get_registry_item, acquire_registry_item, get_registry_acquisition, refresh_registry_snapshot, and 102 more. Their descriptions and schemas cost roughly 18,710 tokens of context every time the server is loaded.

Does the CueFrame MCP server require authentication?

Yes. CueFrame asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the CueFrame MCP server still maintained?

CueFrame is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the CueFrame MCP server?

VerifyMCP ran 13 checks on CueFrame, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.