mcp-chat-cards

Overview Schema Source Related Servers Discussions Admin

Create video card

create_video_card

Renders an HTML video player card for direct mp4/webm files, data:video URIs, or blob URLs, embedding playable clips in chat. Streaming platform page URLs are rejected because they cannot play.

Instructions

Render a card with an HTML video player for a short clip. src must point straight at a video file (mp4/webm): a direct http(s) URL, a small data:video/* URI, or a blob: URL. Streaming platform page URLs (YouTube, Vimeo, Twitch, TikTok, and similar) are REJECTED, because a video element pointed at a player page renders a card that can never play. When no direct video source exists, use create_animation_card to generate an animated clip instead.

Input Schema

Name	Required	Description
`src`	Yes	Direct http(s) URL to a video file, a data:video/* URI, or a blob: URL
`loop`	No
`muted`	No
`title`	Yes
`poster`	No	Still image shown before playback: http(s) URL or data:image/* URI
`autoplay`	No	Start muted playback on render
`subtitle`	No
`description`	No
`contextActions`	No	Right-click menu actions the model anticipates being useful. Choosing one sends its prompt to the conversation; use {{selection}} to include the user's selected text.

Output Schema

Name	Required	Description
`card`	Yes
`parts`	Yes	Split state, present on EVERY card result so one completeness check works for all card types. Cards that cannot split always report {current:1,total:1,hasMore:false}; create_markdown_card and create_code_tour_card pack oversized content into parts and can report more. Read hasMore rather than the card title to decide whether content was withheld.
`display`	No	Present only when the host is not mounting this server's MCP Apps template (see MCP_CHAT_CARDS_RENDER): the card ships as a ready-made visualizer widget instead.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.0-alpha.1.0.1Oct 17, 2026

addedOutput schema / properties / display

Added value: +{
+  "additionalProperties": false,
+  "description": "Present only when the host is not mounting this server's MCP Apps template (see MCP_CHAT_CARDS_RENDER): the card ships as a ready-made visualizer widget instead.",
+  "properties": {
+    "action": {
+      "description": "What the caller must do to put the card in front of the user",
+      "type": "string"
+    },
+    "loading_messages": {
+      "description": "show_widget loading_messages",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "shown": {
+      "description": "False: the user cannot see this card until action is taken",
+      "type": "boolean"
+    },
+    "title": {
+      "description": "show_widget title (snake_case)",
+      "type": "string"
+    },
+    "widget_code": {
+      "description": "show_widget widget_code, passed unchanged",
+      "type": "string"
+    }
+  },
+  "required": [
+    "shown",
+    "action",
+    "title",
+    "loading_messages",
+    "widget_code"
+  ],
+  "type": "object"
+}

Changed4 schema fields changedv0.1.3-alphaAug 21, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

addedOutput schema / properties / parts

Added value: +{
+  "additionalProperties": false,
+  "description": "Split state, present on EVERY card result so one completeness check works for all card types. Cards that cannot split always report {current:1,total:1,hasMore:false}; create_markdown_card and create_code_tour_card pack oversized content into parts and can report more. Read hasMore rather than the card title to decide whether content was withheld.",
+  "properties": {
+    "current": {
+      "description": "Part number this result rendered (1-based)",
+      "type": "number"
+    },
+    "hasMore": {
+      "description": "True when content was withheld; call again with part: current + 1",
+      "type": "boolean"
+    },
+    "total": {
+      "description": "How many parts the content splits into",
+      "type": "number"
+    }
+  },
+  "required": [
+    "current",
+    "total",
+    "hasMore"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "card"
-]New value: +[
+  "card",
+  "parts"
+]

Changed7 schema fields changedv0.1.1-alphaAug 12, 2026
- addedInput schema / properties / autoplay
```
Added value: +{
+  "description": "Start muted playback on render",
+  "type": "boolean"
+}
```
- addedInput schema / properties / poster / description
```
Added value: +"Still image shown before playback: http(s) URL or data:image/* URI"
```
- removedInput schema / properties / poster / format
```
Removed value: -"uri"
```
- addedInput schema / properties / poster / minLength
```
Added value: +1
```
- addedInput schema / properties / src / description
```
Added value: +"Direct http(s) URL to a video file, a data:video/* URI, or a blob: URL"
```
- removedInput schema / properties / src / format
```
Removed value: -"uri"
```
- addedInput schema / properties / src / minLength
```
Added value: +1
```
First observedv0.0.0-alphaAug 10, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden, and it does well: it discloses a hard validation rule (platform page URLs rejected), the accepted source forms, and the rationale (a video element on a player page can never play). It does not cover auth/permission needs or persistence, but the failure-mode disclosure is substantive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core purpose, then the constraint, then the fallback. No filler; every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. The description covers the decisive routing constraint and the fallback path, leaving only secondary parameter behavior to the schema, which is acceptable for a card renderer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 44% (<50%), so the description must compensate. It adds strong meaning for the critical 'src' parameter (accepted formats mp4/webm, http(s)/data:/blob:, rejected platforms) but says nothing about loop, muted, poster, autoplay, subtitle, or contextActions, leaving most parameters to the sparse schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Render a card') plus resource ('HTML video player for a short clip') and implicitly separates itself from the sibling create_animation_card. An agent can distinguish this from other card-creation tools immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it (direct video file sources), when NOT to use it (streaming platform page URLs are REJECTED), and names the alternative (create_animation_card) with the condition that selects it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.