# read_document_text

Returns the document as compact readable blocks, per tab: each paragraph with its text, start/end indexes (UTF-16 code units — the coordinates insert_text/replace_range/delete_range/style tools take), named style (headings) and bullet flag; tables come as cells[row][column] plain text with the table's range. Inline images appear as [image:<objectId>] placeholders (the id feeds replace_image). tab_id limits the output to one tab. Call this before any range edit — every insert/delete shifts later indexes, so indexes from before a mutation are stale.

Agent View of the PolicyLayer registry record for `read_document_text`. HTML page: https://policylayer.com/tools/a1-x-tech-mcp-google-docs/read-document-text

## Facts

- Tool: `read_document_text`
- Server: Mcp Google Docs (`@a1-x-tech/mcp-google-docs`) — https://policylayer.com/tools/a1-x-tech-mcp-google-docs.md
- Install: `npx -y @a1-x-tech/mcp-google-docs`
- Homepage: https://github.com/A1-x-Tech/mcp-google-docs
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `tab_id` | string | no | Tab to target (from list_tabs). Omit for the first/only tab. |
| `document_id` | string | yes | The document id — the long id from the document URL (docs.google.com/document/d/<documentId>/edit) or from create_document output. |

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_document_text",
    "arguments": {
      "document_id": "<document_id>"
    }
  }
}
```

## Why read_document_text is rated Low

Even though read_document_text only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents call read_document_text to retrieve information from Mcp Google Docs 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 Mcp Google Docs:

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

## Other tools on Mcp Google Docs (26)

- `delete_range` — Destructive — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/delete-range.md
- `logout` — Destructive — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/logout.md
- `manage_comment` — Destructive — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/manage-comment.md
- `start_login` — Execute — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/start-login.md
- `style_paragraph` — Execute — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/style-paragraph.md
- `auth_status` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/auth-status.md
- `get_document` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/get-document.md
- `list_comments` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/list-comments.md
- `list_tabs` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/list-tabs.md
- `raw_request` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/raw-request.md
- `style_text` — Read — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/style-text.md
- `create_document` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/create-document.md
- `edit_table` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/edit-table.md
- `export_document` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/export-document.md
- `finish_login` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/finish-login.md
- `import_markdown` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/import-markdown.md
- `insert_break` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-break.md
- `insert_image` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-image.md
- `insert_table` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-table.md
- `insert_text` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/insert-text.md
- `replace_all_text` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/replace-all-text.md
- `replace_image` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/replace-image.md
- `replace_range` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/replace-range.md
- `set_client` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/set-client.md
- `set_paragraph_bullets` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/set-paragraph-bullets.md
- `setup_instructions` — Write — https://policylayer.com/tools/a1-x-tech-mcp-google-docs/setup-instructions.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=a1-x-tech-mcp-google-docs · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a1-x-tech-mcp-google-docs