// SCAN REPORT

LLM2Docs (Unofficial)

50 tools. 44 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 2 Jul 2026

44 can modify or destroy data

6 read-only

50 tools total

Community server · catalogue entry verified 02/07/2026

How to control LLM2Docs (Unofficial) ↓

TOOL MAP

What LLM2Docs (Unofficial) exposes to your agents

Read (6) Write / Execute (41) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous LLM2Docs (Unofficial) tools

Destructive · High delete_table_column This tool permanently removes data (a table column) from a document without the ability to undo via the tool itself. Destructive · High delete_table_row This tool permanently removes table row data from a Google Doc, which cannot be undone programmatically by an AI agent. Destructive · High delete_text This tool permanently removes data from a Google Docs document. Write · Medium transform_text_case This tool modifies existing text content in a Google Doc by changing its case.

44 of LLM2Docs (Unofficial)'s 50 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control LLM2Docs (Unofficial)

PolicyLayer is an MCP gateway — it sits between your AI agents and LLM2Docs (Unofficial), and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_table_column": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_cross_reference": {
    "limits": [
      {
        "counter": "add_cross_reference_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_auth_status": {
    "limits": [
      {
        "counter": "check_auth_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register LLM2Docs (Unofficial) — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LLM2DOCS (UNOFFICIAL) →

Instant setup, no code required.

FULL CATALOGUE

All 50 LLM2Docs (Unofficial) tools

DESTRUCTIVE 3 tools

Destructive delete_table_column Delete a column from a table Destructive delete_table_row Delete a row from a table Destructive delete_text Delete text from a specific range in the document

WRITE 41 tools

Write add_cross_reference Add a cross-reference link to a bookmark or heading Write add_hyperlink Add a hyperlink to text in the document Write add_image_caption Add a caption to an image Write append_text Add text to the end of a Google Document Write apply_font_formatting Apply multiple font formatting options at once Write apply_heading Format text as heading (H1-H6) or title Write apply_subscript Make text subscript Write apply_superscript Make text superscript Write change_font Change the font family of text in a document Write change_font_size Change the font size of text in a document Write change_font_style Change the font style (italic/normal) of text in a document Write change_font_weight Change the font weight (bold/normal) of text in a document Write create_bulleted_list Create a bulleted list with specified items Write create_document Create a new Google Document with optional initial content Write create_formatted_document Create document with title, heading, and formatted body text Write create_numbered_list Create a numbered list with specified items Write find_and_replace Find and replace text in the document Write format_table Apply advanced formatting to tables (borders, colors, alignment) Write format_text Apply bold, italic, or other formatting to text range Write insert_bookmark Insert a bookmark (named anchor) in the document Write insert_drawing Insert a drawing or shape into the document Write insert_footer Insert a footer in the document Write insert_footnote Insert a footnote in the document Write insert_header Insert a header in the document Write insert_image_from_url Insert an image into the document from a URL Write insert_page_break Insert a page break at the specified position Write insert_section_break Insert a section break in the document Write insert_table Insert a table into the document Write insert_table_column Insert a new column into a table Write insert_table_of_contents Insert an auto-generated table of contents Write insert_table_row Insert a new row into a table Write insert_text Insert text at a specific position in the document Write merge_table_cells Merge cells in a table (horizontal or vertical) Write replace_text Replace text in a specific range with new text Write resize_image Resize an image in the document Write set_alignment Set text alignment for a paragraph Write set_image_alignment Set the alignment of an image in the document Write set_line_spacing Set line spacing for paragraphs Write set_paragraph_spacing Set spacing before and after paragraphs Write set_table_column_width Set the width of table columns Write transform_text_case Transform text to uppercase, lowercase, or title case

READ 6 tools

Read check_auth_status Check if the Google Docs MCP server is properly authenticated Read get_word_count Get word count and other document statistics Read read_document Read the complete content of a Google Document Read search_documents Search for documents by name Read search_text_in_document Search for text within the document and return positions Read spell_check Check spelling in the document and get suggestions

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about LLM2Docs (Unofficial)

Can an AI agent delete data through the LLM2Docs (Unofficial) MCP server? +

Yes. The LLM2Docs (Unofficial) server exposes 3 destructive tools including delete_table_column, delete_table_row, delete_text. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through LLM2Docs (Unofficial)? +

The LLM2Docs (Unofficial) server has 41 write tools including add_cross_reference, add_hyperlink, add_image_caption. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach LLM2Docs (Unofficial).

How many tools does the LLM2Docs (Unofficial) MCP server expose? +

50 tools across 4 categories: Destructive, Execute, Read, Write. 6 are read-only. 44 can modify, create, or delete data.

How do I enforce a policy on LLM2Docs (Unofficial)? +

Register the LLM2Docs (Unofficial) MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every LLM2Docs (Unofficial) tool call.

Deterministic rules across all 50 LLM2Docs (Unofficial) tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LLM2DOCS (UNOFFICIAL) →

Instant setup, no code required.

50 LLM2Docs (Unofficial) tools catalogued and risk-classified — across an index of 43,000+ MCP servers.