Plain Com MCP Server

78 tools. 54 can modify or destroy data without limits.

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

Last updated:

54 can modify or destroy data
24 read-only
78 tools total

Community server · catalogue entry verified 29/06/2026

How to control Plain Com MCP Server ↓

What Plain Com MCP Server exposes to your agents

Read (24) Write / Execute (37) Destructive / Financial (17)
Critical Risk

The most dangerous Plain Com MCP Server tools

54 of Plain Com MCP Server's 78 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Plain Com MCP Server

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

Deny destructive operations
{
  "delete_autoresponder": {
    "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_customer_to_groups": {
    "limits": [
      {
        "counter": "add_customer_to_groups_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "change_thread_status_to_todo": {
    "limits": [
      {
        "counter": "change_thread_status_to_todo_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 Plain Com MCP Server — 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 PLAIN COM →

Instant setup, no code required.

All 78 Plain Com MCP Server tools

WRITE 37 tools
Write add_customer_to_groups Add a customer to one or more groups Write add_labels_to_thread Add labels to a thread Write assign_thread Assign a thread to a user Write change_thread_priority Change the priority of a thread Write create_autoresponder Create a new autoresponder Write create_customer_event Create a custom event on a customer timeline Write create_customer_group Create a new customer group Write create_help_center Create a new help center Write create_help_center_article_group Create a new article group (category) in a help center Write create_knowledge_source Create a knowledge source for AI to reference Write create_label_type Create a new label type Write create_note Create an internal note on a thread (not visible to customer) Write create_snippet Create a new snippet (canned response) Write create_thread Create a new support thread for a customer Write create_thread_event Create a custom event on a thread timeline Write create_tier Create a new support tier Write create_webhook Create a new webhook target Write generate_help_center_article Auto-generate a help center article from a support thread using AI Write mark_customer_as_spam Mark a customer as spam Write mark_thread_done Mark a support thread as done/resolved Write mark_thread_todo Mark a support thread as todo (re-open it) Write reply_to_thread Reply to a support thread. The reply will be sent to the customer via the original channel (email, chat, etc.) Write send_chat Send a chat message to a customer Write send_email Send a new email to a customer (starts a new thread) Write snooze_thread Snooze a support thread. Use WAITING_FOR_CUSTOMER (no duration) to snooze until customer replies, or WAITING_F Write update_help_center Update an existing help center Write update_help_center_article_group Update an article group Write update_help_center_custom_domain Set a custom domain for a help center Write update_help_center_index Update the navigation index/structure of a help center Write update_snippet Update an existing snippet Write update_thread_title Update the title of a thread Write update_webhook Update a webhook target Write upsert_company Create or update a company Write upsert_customer Create or update a customer Write upsert_help_center_article Create or update a help center article Write upsert_tenant Create or update a tenant Write upsert_thread_field Set a custom field value on a thread
READ 24 tools
Read change_thread_status_to_todo Change thread status to Todo with optional status detail. Use this instead of mark_thread_todo when you need t Read get_customer Get detailed customer information by ID Read get_help_center Get details of a specific help center Read get_help_center_article Get a specific help center article by ID Read get_help_center_article_by_slug Get a help center article by its URL slug Read get_help_center_article_group Get a specific article group by ID Read get_help_center_index Get the navigation index/structure of a help center Read get_queue_stats Get a quick overview of the support queue with counts by status Read get_thread Get detailed thread information including conversation timeline Read get_workspace Get current workspace information Read list_autoresponders List all autoresponders Read list_customer_groups List all customer groups Read list_help_center_article_groups List article groups (categories) in a help center Read list_help_center_articles List articles in a help center Read list_help_centers List all help centers in the workspace Read list_label_types List all available label types Read list_snippets List all snippets (canned responses) Read list_thread_field_schemas List all custom thread field schemas Read list_threads List support threads with optional filters. Note: statusDetail (CREATED, NEW_REPLY, etc.) is not available in Read list_tiers List all support tiers Read list_users List workspace users Read list_webhooks List all webhook targets Read search_customers Search for customers by email Read verify_help_center_custom_domain Verify DNS ownership of a custom domain for a help center

Related servers

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

Questions about Plain Com MCP Server

Can an AI agent delete data through the Plain Com MCP Server MCP server? +

Yes. The Plain Com MCP Server server exposes 17 destructive tools including delete_autoresponder, delete_company, delete_customer. 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 Plain Com MCP Server? +

The Plain Com MCP Server server has 37 write tools including add_customer_to_groups, add_labels_to_thread, assign_thread. 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 Plain Com MCP Server.

How many tools does the Plain Com MCP Server MCP server expose? +

78 tools across 3 categories: Destructive, Read, Write. 24 are read-only. 54 can modify, create, or delete data.

How do I enforce a policy on Plain Com MCP Server? +

Register the Plain Com MCP Server 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 Plain Com MCP Server tool call.

Deterministic rules across all 78 Plain Com MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

78 Plain Com MCP Server 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.