generate_ai_metadata
Generate AI metadata SUGGESTIONS for one video (title, description, keywords, genre, etc.). Safe - the video is NOT modified. Suggestions are returned for review. - Returns immediately with the finished values (this call is synchronous) - Creates one session per requested attribute, each with its...
This record as markdown: /tools/com-zype-mcp-server/generate-ai-metadata.md
What generate_ai_metadata does on Zype Com
AI agents use generate_ai_metadata to create or update resources in Zype Com, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zype Com environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
video_id | string | Yes | The video ID to generate suggestions for (required) |
attributes | array | — | Attributes to generate: title, friendly_title, description, short_description, keywords, genre. Omit for Zype defaults. |
prompt_context_id | string | — | Optional prompt context ID (brand voice / style guide configured in Zype) to steer generation |
Parameters from the server's own tool schema.
Why generate_ai_metadata is rated Medium
An AI agent can call generate_ai_metadata faster than any human can review: one bad instruction and it creates or modifies resources in Zype Com by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs generate_ai_metadata safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Zype Com, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For generate_ai_metadata, this is the rule to start with:
generate_ai_metadata stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Zype Com, apply this rule, and every generate_ai_metadata call is checked against it from then on.
Questions about generate_ai_metadata
Generate AI metadata SUGGESTIONS for one video (title, description, keywords, genre, etc.). Safe - the video is NOT modified. Suggestions are returned for review. - Returns immediately with the finished values (this call is synchronous) - Creates one session per requested attribute, each with its own session_id - To write a value, call apply_ai_metadata with that attribute's session_id (once per attribute) - Requires a completed transcript on the video, otherwise the API returns 422 (see transcribe_video). It is categorised as a Write tool in the Zype Com MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
generate_ai_metadata accepts 3 parameters: video_id, attributes, prompt_context_id. Required: video_id. The full parameter table on this page comes from the server's own tool schema.
Register the Zype Com MCP server in PolicyLayer and add a rule for generate_ai_metadata: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Zype Com. Nothing to install.
generate_ai_metadata is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_ai_metadata rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for generate_ai_metadata. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
generate_ai_metadata is provided by the Zype Com MCP server (zype/zype-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Zype Com, and thousands of servers like it.
This server
Across the catalogue