# read_docs

Return a canonical Clipkit doc as text. topic "card" = the ~8KB compact authoring card — the recommended context for authoring; "pattern-data-viz" / "pattern-cinematic-ui" / "pattern-ui-screencast" = ~4-5KB archetype 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.)

Agent View of the PolicyLayer registry record for `read_docs`. HTML page: https://policylayer.com/tools/dev-clipkit-clipkit/read-docs

## Facts

- Tool: `read_docs`
- 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 |
| --- | --- | --- | --- |
| `topic` | string | no | Which doc. Default "agents". |

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": "read_docs",
    "arguments": {}
  }
}
```

## Why read_docs is rated Low

Tool retrieves and returns documentation and reference materials with no side effects or modifications.

From the tool's own definition: "Return a canonical Clipkit doc as text; load documentation and reference materials."

## Use case

AI agents call read_docs 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": {
    "read_docs": {}
  }
}
```

## 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
- `get_schema` — Read — https://policylayer.com/tools/dev-clipkit-clipkit/get-schema.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
- `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