# get_schema

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.

Agent View of the PolicyLayer registry record for `get_schema`. HTML page: https://policylayer.com/tools/dev-clipkit-clipkit/get-schema

## Facts

- Tool: `get_schema`
- Server: Clipkit (`https://www.clipkit.dev/mcp`) — https://policylayer.com/tools/dev-clipkit-clipkit.md
- Homepage: https://github.com/clipkit-video/clipkit
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 1
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `element_type` | string | no | Limit to one element type's fields (e.g. "text"). Omit for the full Source schema (large). |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_schema",
    "arguments": {}
  }
}
```

## Why get_schema is rated Low

This tool retrieves schema metadata about Clipkit Sources and their element types. It performs a query operation that returns information without modifying, deleting, or executing any operations. The purpose is purely informational—to help authors understand field names, types, and enums for reference during development. No data is created, modified, deleted, or executed.

From the tool's own definition: "Tool description states 'Return the authoritative JSON Schema' and 'Call with no argument for the full Source schema, or with element_type...for just that element's fields.' The verb 'Return' and action of retrieving/querying schema information indicates a…"

## Use case

AI agents call get_schema to retrieve information from Clipkit without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Clipkit:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_schema": {}
  }
}
```

## Other tools on Clipkit (14)

- `delete_element` — Destructive — https://policylayer.com/tools/dev-clipkit-clipkit/delete-element.md
- `describe_project` — Read — https://policylayer.com/tools/dev-clipkit-clipkit/describe-project.md
- `get_project` — Read — https://policylayer.com/tools/dev-clipkit-clipkit/get-project.md
- `open_in_editor` — Read — https://policylayer.com/tools/dev-clipkit-clipkit/open-in-editor.md
- `preview_still` — Read — https://policylayer.com/tools/dev-clipkit-clipkit/preview-still.md
- `read_docs` — Read — https://policylayer.com/tools/dev-clipkit-clipkit/read-docs.md
- `validate_project` — Read — https://policylayer.com/tools/dev-clipkit-clipkit/validate-project.md
- `add_element` — Write — https://policylayer.com/tools/dev-clipkit-clipkit/add-element.md
- `create_project` — Write — https://policylayer.com/tools/dev-clipkit-clipkit/create-project.md
- `create_promo` — Write — https://policylayer.com/tools/dev-clipkit-clipkit/create-promo.md
- `edit_element` — Write — https://policylayer.com/tools/dev-clipkit-clipkit/edit-element.md
- `ingest_asset` — Write — https://policylayer.com/tools/dev-clipkit-clipkit/ingest-asset.md
- `load_project` — Write — https://policylayer.com/tools/dev-clipkit-clipkit/load-project.md
- `set_project` — Write — https://policylayer.com/tools/dev-clipkit-clipkit/set-project.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=dev-clipkit-clipkit · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-clipkit-clipkit