NapCat MCP Server

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

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

Last updated:

23 can modify or destroy data
34 read-only
57 tools total

Community server · catalogue entry checked 25/07/2026

How to control NapCat MCP Server ↓

What NapCat MCP Server exposes to your agents

Read (34) Write / Execute (19) Destructive / Financial (4)
Critical Risk

The most dangerous NapCat MCP Server tools

23 of NapCat MCP Server's 57 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control NapCat MCP Server

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

Deny destructive operations
{
  "delete_essence_msg": {
    "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
{
  "mark_msg_as_read": {
    "limits": [
      {
        "counter": "mark_msg_as_read_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "can_send_image": {
    "limits": [
      {
        "counter": "can_send_image_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 NapCat 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 NAPCAT →

Instant setup, no code required.

All 57 NapCat MCP Server tools

READ 34 tools
Read can_send_image Check if can send image Read can_send_record Check if can send voice record Read get_cookies Get cookies Read get_credentials Get credentials Read get_csrf_token Get CSRF token Read get_essence_msg_list Get group essence message list Read get_forward_msg Get forward message Read get_friend_list Get friend list Read get_friend_msg_history Get friend message history Read get_group_announcement_list Get group announcement list Read get_group_at_all_remain Get remaining @all count for group Read get_group_file_system_info Get group file system information Read get_group_file_url Get group file download URL Read get_group_files_by_folder Get file list in specified group folder Read get_group_honor_info Get group honor information Read get_group_ignore_add_request Get group ignored join requests Read get_group_info Get group detailed information Read get_group_info_ex Get group detailed information (extended) Read get_group_list Get list of all joined groups Read get_group_member_info Get specified group member detailed info Read get_group_member_list Get group member list Read get_group_msg_history Get group message history with IDs and structured OneBot fields for pagination or follow-up actions Read get_group_root_files Get group root directory file list Read get_group_system_msg Get group system messages Read get_image Get image information Read get_login_info Get login account information Read get_msg Get message details Read get_online_client Get online client list Read get_record Get voice record information Read get_status Get running status Read get_stranger_info Get stranger information Read get_version_info Get version information Read ocr_image OCR image recognition Read read_group_messages Read recent group messages as a minimal human-readable timeline. Prefer this for understanding chat; use get_g

Related servers

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

Questions about NapCat MCP Server

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

Yes. The NapCat MCP Server server exposes 4 destructive tools including delete_essence_msg, delete_group_file, delete_msg. 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 NapCat MCP Server? +

The NapCat MCP Server server has 17 write tools including mark_msg_as_read, send_group_forward_msg, send_group_msg. 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 NapCat MCP Server.

How many tools does the NapCat MCP Server MCP server expose? +

57 tools across 3 categories: Destructive, Read, Write. 34 are read-only. 23 can modify, create, or delete data.

How do I enforce a policy on NapCat MCP Server? +

Register the NapCat 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 NapCat MCP Server tool call.

Deterministic rules across all 57 NapCat MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

57 NapCat MCP Server tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from NapCat MCP Server's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.