// SCAN REPORT

DocAgent

11 tools. 4 can modify or destroy data without limits.

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

Last updated: 1 Jul 2026

4 can modify or destroy data

7 read-only

11 tools total

Community server · catalogue entry verified 01/07/2026

How to control DocAgent ↓

TOOL MAP

What DocAgent exposes to your agents

Read (7) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous DocAgent tools

Execute · High run_unified_workflow This tool executes a sophisticated multi-component workflow (docagent + orchestrator) that produces side effects (documentation generation, file creation). Write · Medium generate_all This tool generates and creates documentation artifacts (requirements, design specs, test strategies, deployment guides per server description), which are new files/content being written to storage. Write · Low generate_documents The tool creates new document artifacts without destructive capability. Write · Low zip_outputs This tool creates (writes) a new zip file from existing outputs, which is a reversible file operation.

4 of DocAgent's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control DocAgent

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

Rate limit write operations

{
  "generate_all": {
    "limits": [
      {
        "counter": "generate_all_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "hello": {
    "limits": [
      {
        "counter": "hello_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 DocAgent — 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 DOCAGENT →

Instant setup, no code required.

FULL CATALOGUE

All 11 DocAgent tools

EXECUTE 1 tools

Execute run_unified_workflow Run the unified workflow with both docagent and orchestrator working together automatically

WRITE 3 tools

Write generate_all Generate all documents Write generate_documents Generate specific documents Write zip_outputs Create zip of all outputs

READ 7 tools

Read hello Say hello to someone Read list_outputs List generated outputs Read list_tools List available tools Read orchestrate_docgen_tool Orchestrate document generation with profile selection Read ping Health check endpoint Read show_doc Show document content Read simple_ping Simple ping function

EXPLORE

Related servers

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

FAQ

Questions about DocAgent

How do I prevent bulk modifications through DocAgent? +

The DocAgent server has 3 write tools including generate_all, generate_documents, zip_outputs. 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 DocAgent.

How many tools does the DocAgent MCP server expose? +

11 tools across 3 categories: Execute, Read, Write. 7 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on DocAgent? +

Register the DocAgent 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 DocAgent tool call.

Deterministic rules across all 11 DocAgent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DOCAGENT →

Instant setup, no code required.

11 DocAgent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.