// SCAN REPORT

MCP Document Processor

10 tools. 6 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

6 can modify or destroy data

4 read-only

10 tools total

Community server · catalogue entry verified 02/07/2026

How to control MCP Document Processor ↓

TOOL MAP

What MCP Document Processor exposes to your agents

Read (4) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP Document Processor tools

Execute · Medium fact-check This tool triggers external operations (live web search via a separate MCP, get-web-search-summaries) and optionally writes output files. Write · Medium create-pptx This tool creates new PowerPoint files, which is a reversible write operation. Write · Medium edit-doc This tool modifies existing DOCX documents reversibly. Write · High edit-excel The tool modifies existing Excel files (XLSX format) reversibly.

6 of MCP Document Processor's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Document Processor

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

Rate limit write operations

{
  "create-pptx": {
    "limits": [
      {
        "counter": "create-pptx_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "drift-monitor": {
    "limits": [
      {
        "counter": "drift-monitor_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 MCP Document Processor — 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 MCP DOCUMENT PROCESSOR →

Instant setup, no code required.

FULL CATALOGUE

All 10 MCP Document Processor tools

EXECUTE 1 tools

Execute fact-check Fact-check a document (or explicit claims) against the LIVE WEB. CROSS-MCP tool: doc-processor extracts the cl

WRITE 4 tools

Write create-pptx Create an EDITABLE PowerPoint presentation (.pptx) you can open in PowerPoint / Keynote / Google Slides. USE w Write edit-doc Edit an existing DOCX. Actions: Write edit-excel Edit an existing XLSX workbook. Actions: Write edit-pptx Edit an existing PowerPoint (.pptx). Actions:

READ 4 tools

Read drift-monitor Monitor documents for structural drift over time. Actions: Read get-lineage Trace the provenance chain of a document. Returns a tree { sources: [{filePath, ...}], derivatives: [{filePath Read list-documents Search the document registry. Filters compose with AND-logic: category match AND tag match AND title-substring Read list-templates List available document templates AND blueprints. Templates are static, named structures (e.g.

OTHER 1 tools

Other dna Manage the project

FAQ

Questions about MCP Document Processor

How do I prevent bulk modifications through MCP Document Processor? +

The MCP Document Processor server has 4 write tools including create-pptx, edit-doc, edit-excel. 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 MCP Document Processor.

How many tools does the MCP Document Processor MCP server expose? +

10 tools across 2 categories: Read, Write. 4 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on MCP Document Processor? +

Register the MCP Document Processor 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 MCP Document Processor tool call.

Deterministic rules across all 10 MCP Document Processor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP DOCUMENT PROCESSOR →

Instant setup, no code required.

10 MCP Document Processor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.