clipkit MCP server
dev.clipkit/clipkitclipkit.devstreamable-httpv1.0.0Scanned
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
15 tools: 4 can delete or cancel things, 6 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 5
- Can send data out · 1
- 5 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the clipkit MCP server can do
The clipkit MCP server is published by clipkit.dev, a domain the MCP Registry verified. It has 15 tools. It can delete or cancel things (4 tools: set_project, delete_element, create_promo and load_project) and create or change data (6 tools: create_project, add_element, edit_element, validate_project and 2 more). 5 tools only read.
1 tool reads private data (read_docs); 5 tools bring in text other people can write (preview_still, create_promo, open_in_editor and 2 more); 1 tool can send data out of your system (ingest_asset). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 5 findings (annotation-conflict and base64-blob). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
15 tools
Deletes or cancels 4Claude Code: deny
create_promoAssemble a designed-looking promo/intro/product/data video from the Clipkit pattern library: give an ordered list of SCENES and the words, and it bakes in the camera, glass, lighti…Reads text others write3 findings
Why it is in this group
- The name "create_promo" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.scenes.items.anyOf[1].properties.color.$ref contains a 49-character base64 string.
What this check looks forMatched text
inputSchema.properties.scenes.items.anyOf[1].properties.color.$ref: "#/properties/scenes/items/anyOf/0/properties/color"
- Warn
The input schema at properties.scenes.items.anyOf[1].properties.duration.$ref contains a 52-character base64 string.
What this check looks forMatched text
inputSchema.properties.scenes.items.anyOf[1].properties.duration.$ref: "#/properties/scenes/items/anyOf/0/properties/duration"
- Warn
The input schema at properties.scenes.items.anyOf[2].properties.color.$ref contains a 49-character base64 string.
What this check looks forMatched text
inputSchema.properties.scenes.items.anyOf[2].properties.color.$ref: "#/properties/scenes/items/anyOf/0/properties/color"
Description, as the server wrote it Assemble a designed-looking promo/intro/product/data video from the Clipkit pattern library: give an ordered list of SCENES and the words, and it bakes in the camera, glass, lighting, motion blur, timing, and layout, then returns an editor link. This is a FAST option when a conventional promo structure fits — it is NOT the only way to make a video and NOT a default; for anything specific or original, author the JSON yourself and call set_project (the full creative range). When you do use this, MIX scene types to fit the brief and vary the structure — a video can be a single kinetic headline, three title cards, a showcase montage, or a data explainer; you do NOT need a hero or a cta. Scene types: hero (glass-orb logo reveal: wordmark, tagline?), kinetic (letter-fly headline: text, subtitle?), showcase (a screenshot tilted in 3D: screenshot URL), title (full-frame title card: headline, kicker?, subtitle?), cta (closing card with a glass button: wordmark, tagline?, cta), stats (hero numbers: stats[{label,current,previous?}], title?), bars (bar chart: bars[{label,value,previous?}], title?), ranking (top-N list: items[{label,value}], title?), pie (pie cards: cards[{label,value,total,previous?}], title?). The data scenes (stats/bars/ranking/pie) look best with theme "mux".
Annotations the server declares
- title: Compose a designed promo from prebuilt scenes (one fast option)
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
delete_elementDelete the element with the given id, anywhere in the tree (including one nested inside a group or its mask) — a tweak to an existing composition.No findings
Why it is in this group
- The name "delete_element" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete the element with the given id, anywhere in the tree (including one nested inside a group or its mask) — a tweak to an existing composition. (The project must keep at least one top-level element.)
Annotations the server declares
- title: Delete one element by id
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
load_projectImport a previously shared project as the current project, by its share id or its editor URL (e.g.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "import": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Import a previously shared project as the current project, by its share id or its editor URL (e.g. https://clipkit.dev/editor?id=…), returning its project_id. Use this to continue working on a project the user opened in the editor or shared earlier — the round-trip for open_in_editor. Pass an existing project_id to load into that project; omit it to load into a new one.
Annotations the server declares
- title: Load a shared project back into the session
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
set_projectReplace the entire project with the given source JSON, returning its project_id.No findings
Why it is in this group
- The name "set_project" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Replace the entire project with the given source JSON, returning its project_id. This is the PRIMARY way to build: use it to create a composition or to add/change many elements at once. (To tweak a single element in an existing project, use edit_element / add_element / delete_element instead.) REVISION RULE: if you are iterating on a video that already exists in this conversation — the user asked for changes, you are fixing your own work — you MUST pass its project_id so the project is updated in place and keeps one editor link and its version history. Omitting project_id creates a NEW, unrelated project and strands the old one; only omit for a genuinely different video. The input is validated against the @clipkit/protocol before being accepted; invalid inputs return an error. Shape: { width, height, duration, frame_rate, output_format, background_color?, defaults? (house easing, e.g. a spring), fonts?, camera?, lights?, elements:[…] }; every element has a `type` plus base fields (id, layer, x, y, width, height, time, duration, opacity, rotation, animations, keyframe_animations) and type-specific fields. CKP/1.1: keyframe easings accept a spring object {type:"spring", duration?, bounce?}; channels take stagger {each, from, ease, split, seed} to spread across text units / set copies / group children; groups take layout {direction, gap, align} (stack — no hand-computed positions); text takes a count-up {expr, format}. For exact field names + types call get_schema (optionally with an element_type) — the runtime ignores unrecognized keys, and this tool flags any it does not recognize.
Annotations the server declares
- title: Replace the entire Clipkit project
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
Changes things 6Claude Code: ask
add_elementAppend a single element to an existing project — a TWEAK, e.g.No findings
Why it is in this group
- The name "add_element" says "add": a word for a change.
Description, as the server wrote it Append a single element to an existing project — a TWEAK, e.g. dropping in one more caption or shape. By default it is added at the top level; pass parent_id to add it INTO a group (nested). The element is any valid schema element: video, image, text, shape, audio, group, caption, or particles. To create a composition or add several elements at once, build the JSON and use set_project instead. The new element is validated as part of the project as a whole before being added. Call get_schema(element_type) for the exact per-type fields; unrecognized keys are flagged.
Annotations the server declares
- title: Add an element to the current project
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
create_projectCreate a new, blank Clipkit project with the given dimensions and duration, and return its project_id.No findings
Why it is in this group
- The name "create_project" says "create": a word for a change.
Description, as the server wrote it Create a new, blank Clipkit project with the given dimensions and duration, and return its project_id. Defaults: 1920×1080, 10 seconds, 30 fps, output_format "mp4". Call this first when starting a new video. Pass an existing project_id to reset that project to blank; omit it to start a fresh project (note the returned id for subsequent tools).
Annotations the server declares
- title: Create a new Clipkit project
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
edit_elementChange fields on the element with the given id by merging in a partial element — only the keys you include change.No findings
Why it is in this group
- The name "edit_element" says "edit": a word for a change.
Description, as the server wrote it Change fields on the element with the given id by merging in a partial element — only the keys you include change. The id may be any element ANYWHERE in the tree, including one nested inside a group (or its mask). Pass a whole nested value (e.g. a new `keyframe_animations` array) to replace that key; set a key to null to remove it. This is for TWEAKING an existing composition. To create a composition or change many elements at once, edit the JSON and call set_project instead. The result is re-validated before being accepted.
Annotations the server declares
- title: Tweak one existing element (merge changed fields)
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
ingest_assetFetch a remote media URL (image/video/audio) and HOST it on Clipkit, returning a stable asset_url to put in an element's `url`.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "fetch": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "ingest_asset" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "fetch": a word for reading.
Description, as the server wrote it Fetch a remote media URL (image/video/audio) and HOST it on Clipkit, returning a stable asset_url to put in an element's `url`. Use this so the project's media survives — the original link may rot, be private, or block hotlinking. Anonymous projects allow up to 5 hosted assets / 100 MB total / 50 MB per file; when the limit is hit, tell the user to open the project (open_in_editor) and sign in to add more. Requires project_id.
Annotations the server declares
- title: Host a remote image/video/audio so a project can use it
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
open_in_editorValidate the current project and create a link that opens it in the Clipkit web editor, where the user can preview and refine it.Reads text others writeNo findings
Why it is in this group
- The name "open_in_editor" says "open": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "validate" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it Validate the current project and create a link that opens it in the Clipkit web editor, where the user can preview and refine it. This shares the PROJECT (nothing is rendered — that's render_video). Use after composing or editing. Returns a URL.
Annotations the server declares
- title: Create a shareable link that opens the current project in the editor
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
validate_projectRun the @clipkit/protocol validator against the current project AND surface render-time warnings even when the JSON is valid — things that pass the schema but the runtime will sile…1 finding
Why it is in this group
- The name "validate_project" says "validate": a word for reading.
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "validate_project" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "validate_project" says "validate": a word for reading.
Description, as the server wrote it Run the @clipkit/protocol validator against the current project AND surface render-time warnings even when the JSON is valid — things that pass the schema but the runtime will silently drop or clip: emoji / non-ASCII text (the runtime font atlas is ASCII-only), elements that run past the composition end, a missing top-level duration. Run it before you share or render the project. For a fuller timeline read-back, use describe_project.
Annotations the server declares
- title: Validate the current project (schema + render-time warnings)
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
Only reads 5Show 5 read-only tools
describe_projectReturn a compact, human-readable summary of the current project — dimensions, fps, duration, an element breakdown by type, a per-track timeline (paint order low→high), and render-t…No findings
Why it is in this group
- The name "describe_project" says "describe": a word for reading.
Description, as the server wrote it Return a compact, human-readable summary of the current project — dimensions, fps, duration, an element breakdown by type, a per-track timeline (paint order low→high), and render-time warnings. Much cheaper to read than get_project's full JSON; use it to orient yourself or sanity-check structure without dumping the whole source.
Annotations the server declares
- title: Describe the current project in plain language
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_projectReturn the full current Clipkit source as JSON.No findings
Why it is in this group
- The name "get_project" says "get": a word for reading.
Description, as the server wrote it Return the full current Clipkit source as JSON. Use this to inspect the project, pass it to a render pipeline, or compose follow-up edits.
Annotations the server declares
- title: Get the current Clipkit project JSON
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_schemaReturn the authoritative JSON Schema for a Clipkit Source — exact field names, types, and enums, generated from the protocol.No findings
Why it is in this group
- The name "get_schema" says "get": a word for reading.
Description, as the server wrote it Return the authoritative JSON Schema for a Clipkit Source — exact field names, types, and enums, generated from the protocol. Call with no argument for the full Source schema, or with element_type (e.g. "text", "shape", "particles") for just that element's fields (much smaller). Use this when authoring with set_project / add_element so you never guess a field.
Annotations the server declares
- title: Get the Clipkit JSON Schema (exact fields)
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
preview_stillRender a single frame of the current project to a PNG and return it as an image you can look at.Reads text others writeNo findings
Why it is in this group
- The name "preview_still" says "preview": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Render a single frame of the current project to a PNG and return it as an image you can look at. This is how you check your work — in chat there is no other way to see what a composition actually looks like. Use it liberally: after composing, after edits, and at different times to inspect motion. Stills are FREE (credits are only spent by render_video). Pass `time` (seconds) to choose the frame; defaults to 0.
Annotations the server declares
- title: Render one frame of the current project so you can SEE it
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
read_docsReturn a canonical Clipkit doc as text.Reads private dataNo findings
Why it is in this group
- The name "read_docs" says "read": a word for reading.
What it can reach
- private-dataThe name "read_docs" says "read" and "doc": it reads documents.
- private-dataThe description's first sentence says "return" and "doc": it reads documents.
Description, as the server wrote it Return a canonical Clipkit doc as text. topic "card" = the ~8KB compact authoring card — the recommended context for authoring; "pattern-lighting" = the shine/neon/glow technique rigs; "pattern-data-viz" / "pattern-cinematic-ui" / "pattern-ui-screencast" / "pattern-promo-teaser" = ~4-5KB pattern cards (proven idioms: count-ups and bar rows; product hero shots with camera rigs; faked app UI with typing/cursor/clicks) — load ONE alongside the card when the brief matches its archetype; "agents" = the full authoring guide (fetch only when the card doesn't cover a need); "protocol" = the formal field spec; "brand" = brand reference. (Same docs offered as MCP resources, exposed as a tool so you can read them directly — resources are not always model-readable.)
Annotations the server declares
- title: Read the Clipkit authoring docs
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
5 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__clipkit__ingest_asset"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:51 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (4 destructive, 6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.clipkit.dev/mcp: tools/list returned 15 tools to an anonymous client, including set_project (destructive), delete_element (destructive), create_promo (destructive), load_project (destructive), create_project (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
- Warnvalidate_project
The server marks "validate_project" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "validate_project" says "validate": a word for reading.
- Warncreate_promo
The input schema at properties.scenes.items.anyOf[1].properties.color.$ref contains a 49-character base64 string.
What this check looks forMatched text
inputSchema.properties.scenes.items.anyOf[1].properties.color.$ref: "#/properties/scenes/items/anyOf/0/properties/color"
- Warncreate_promo
The input schema at properties.scenes.items.anyOf[1].properties.duration.$ref contains a 52-character base64 string.
What this check looks forMatched text
inputSchema.properties.scenes.items.anyOf[1].properties.duration.$ref: "#/properties/scenes/items/anyOf/0/properties/duration"
- Warncreate_promo
The input schema at properties.scenes.items.anyOf[2].properties.color.$ref contains a 49-character base64 string.
What this check looks forMatched text
inputSchema.properties.scenes.items.anyOf[2].properties.color.$ref: "#/properties/scenes/items/anyOf/0/properties/color"
- Warningest_asset
The server marks "ingest_asset" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The description's first verb is "fetch": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http clipkit https://www.clipkit.dev/mcpclaude mcp add --transport http clipkit https://www.clipkit.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__clipkit__read_docs",
"mcp__clipkit__get_schema",
"mcp__clipkit__get_project",
"mcp__clipkit__describe_project",
"mcp__clipkit__preview_still"
],
"ask": [
"mcp__clipkit__create_project",
"mcp__clipkit__add_element",
"mcp__clipkit__edit_element",
"mcp__clipkit__validate_project",
"mcp__clipkit__open_in_editor",
"mcp__clipkit__ingest_asset"
],
"deny": [
"mcp__clipkit__set_project",
"mcp__clipkit__delete_element",
"mcp__clipkit__create_promo",
"mcp__clipkit__load_project"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as clipkit. Review it before you use it.
Capability tags behind 6 rules
- mcp__clipkit__read_docs private-data
- mcp__clipkit__preview_still untrusted-input
- mcp__clipkit__create_promo untrusted-input
- mcp__clipkit__open_in_editor untrusted-input
- mcp__clipkit__ingest_asset untrusted-input, outbound
- mcp__clipkit__load_project untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.clipkit/clipkit/verify?hash=f93b52fc626c51ededab4176c28f71e367cd1cb5c98760b07ee864cfebcfd0d5" | jq -e '.changed == false'Pinned hash f93b52fc626c, from Nov 11, 2026, 07:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.clipkit/clipkit/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.clipkit/clipkit)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:11 UTC.
clipkit MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the clipkit MCP server safe?
- No scan can promise that. What its definitions show: 15 tools, 10 of which can change, send or delete something, and 5 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the clipkit MCP server delete data?
- Yes. 4 tools can delete, cancel or revoke something: set_project, delete_element, create_promo and load_project.
Can the clipkit MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the clipkit MCP server have?
- 15 tools: 4 destructive, 6 write, 5 read. set_project, delete_element, create_promo, load_project, create_project, add_element, edit_element, validate_project and 7 more.
Does the clipkit MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the clipkit MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): ingest_asset.
Has the clipkit MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.