MCP Help Scout

48 tools. 23 can modify or destroy data without limits.

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

Last updated:

23 can modify or destroy data
25 read-only
48 tools total

Community server · catalogue entry verified 03/07/2026

How to control MCP Help Scout ↓

What MCP Help Scout exposes to your agents

Read (25) Write / Execute (16) Destructive / Financial (7)
Critical Risk

The most dangerous MCP Help Scout tools

23 of MCP Help Scout's 48 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control MCP Help Scout

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

Deny destructive operations
{
  "docs_delete_article": {
    "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
{
  "docs_create_article": {
    "limits": [
      {
        "counter": "docs_create_article_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "docs_get_article": {
    "limits": [
      {
        "counter": "docs_get_article_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register MCP Help Scout — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON MCP HELP SCOUT →

Instant setup, no code required.

All 48 MCP Help Scout tools

READ 25 tools
Read docs_get_article Get a full Docs article by ID or number, including its text content. Read docs_get_category Get a specific Docs category by ID Read docs_get_collection Get a specific Docs collection by ID Read docs_get_redirect Get a specific URL redirect by ID Read docs_get_revision Get a specific article revision by revision ID Read docs_get_site Get a specific Docs site by ID Read docs_list_articles List articles in a Docs collection or category. Returns ArticleRef objects (not full article text). Read docs_list_categories List categories in a Docs collection Read docs_list_collections List all Docs collections. Optionally filter by site, visibility, or sort. Read docs_list_redirects List URL redirects for a Docs site Read docs_list_related_articles List articles related to a specific Docs article Read docs_list_revisions List all revisions of a Docs article Read docs_list_sites List all Docs sites in Help Scout Read docs_search_articles Search for Docs articles by query string. Returns ArticleSearch objects with preview text. Read inbox_get_conversation Get a specific conversation by ID with full details Read inbox_get_customer Get a specific customer by ID Read inbox_get_mailbox Get a specific mailbox by ID Read inbox_get_me Get the authenticated user (resource owner) Read inbox_get_user Get a specific user by ID Read inbox_list_conversations List conversations from the Help Scout Inbox. Supports filtering by mailbox, status, tag, assignee. Read inbox_list_customers List customers in Help Scout. Supports filtering and search. Read inbox_list_mailboxes List all mailboxes in Help Scout Read inbox_list_tags List all tags in Help Scout Read inbox_list_threads List all threads in a conversation Read inbox_list_users List all users (team members) in Help Scout

Related servers

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

Questions about MCP Help Scout

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

Yes. The MCP Help Scout server exposes 7 destructive tools including docs_delete_article, docs_delete_category, docs_delete_collection. 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 MCP Help Scout? +

The MCP Help Scout server has 16 write tools including docs_create_article, docs_create_category, docs_create_collection. 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 Help Scout.

How many tools does the MCP Help Scout MCP server expose? +

48 tools across 3 categories: Destructive, Read, Write. 25 are read-only. 23 can modify, create, or delete data.

How do I enforce a policy on MCP Help Scout? +

Register the MCP Help Scout 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 Help Scout tool call.

Deterministic rules across all 48 MCP Help Scout tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

48 MCP Help Scout tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.