// SCAN REPORT

DocShark

5 tools. 1 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 30/06/2026

How to control DocShark ↓

TOOL MAP

What DocShark exposes to your agents

Read (4) Write / Execute (0) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous DocShark tools

Destructive · High manage_library The tool spans multiple categories (Write for add/rename/refresh, Destructive for remove), so per the rules the most severe applicable category is chosen.

1 of DocShark's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control DocShark

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

Deny destructive operations

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

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

Cap read operations

{
  "get_doc_page": {
    "limits": [
      {
        "counter": "get_doc_page_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 DocShark — 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 DOCSHARK →

Instant setup, no code required.

FULL CATALOGUE

All 5 DocShark tools

DESTRUCTIVE 1 tools

Destructive manage_library Manage library lifecycle: add/rename/refresh/remove/info. Destructive actions require confirmation.

READ 4 tools

Read get_doc_page Retrieve complete documentation page as markdown. Read list_libraries List indexed documentation libraries. Paginated results. Read search_docs Search indexed docs by keyword or library. Returns ranked sections with URLs. Read search_docs_batch Run multiple documentation searches in one call. Use this for repeated or decomposed lookups.

FAQ

Questions about DocShark

Can an AI agent delete data through the DocShark MCP server? +

Yes. The DocShark server exposes 1 destructive tools including manage_library. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the DocShark MCP server expose? +

5 tools across 2 categories: Read, Write. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on DocShark? +

Register the DocShark 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 DocShark tool call.

Deterministic rules across all 5 DocShark tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DOCSHARK →

Instant setup, no code required.

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