PromptingBox MCP Server

29 tools. 18 can modify or destroy data without limits.

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

Last updated:

18 can modify or destroy data
11 read-only
29 tools total

Community server · catalogue entry verified 03/07/2026

How to control PromptingBox MCP Server ↓

What PromptingBox MCP Server exposes to your agents

Read (11) Write / Execute (14) Destructive / Financial (4)
Critical Risk

The most dangerous PromptingBox MCP Server tools

18 of PromptingBox MCP Server's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control PromptingBox MCP Server

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

Deny destructive operations
{
  "delete_folder": {
    "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_context_source": {
    "limits": [
      {
        "counter": "add_context_source_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "find_relevant": {
    "limits": [
      {
        "counter": "find_relevant_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 PromptingBox 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 PROMPTINGBOX →

Instant setup, no code required.

All 29 PromptingBox MCP Server tools

WRITE 14 tools
Write add_context_source Attach a context source to a prompt. Send the extracted text content directly — useful for adding file content Write add_tags Set tags on a prompt (by tag name). This replaces all existing tags on the prompt. Tags are auto-created if th Write create_folder Create a new folder in PromptingBox. Supports one level of nesting — provide parentId or parentName to create Write duplicate_prompt Create a copy of an existing prompt. The copy gets Write move_folder Move a folder under a parent folder (nest it) or to the top level. Supports one level of nesting only. Write move_prompt_to_folder Move a prompt to a different folder. Provide either the prompt ID or the prompt title — if a title is given, i Write publish_prompt Publish a prompt to your public profile on PromptingBox. Makes it visible at /prompt/@username/slug. Requires Write rename_folder Rename an existing folder in PromptingBox. Write restore_version Restore a prompt to a previous version. Creates a new version with the restored content. Write save_prompt Save a prompt to the user\ Write toggle_favorite Star or unstar a prompt in PromptingBox. Write unpublish_prompt Unpublish a prompt, removing it from your public profile. The prompt is not deleted — it becomes private again Write update_prompt Update the title and/or content of an existing prompt. If content changes, a new version is automatically crea Write use_template Save a public template to your PromptingBox collection. Creates a copy you can edit and customize.

Related servers

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

Questions about PromptingBox MCP Server

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

Yes. The PromptingBox MCP Server server exposes 4 destructive tools including delete_folder, delete_prompt, delete_tag. 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 PromptingBox MCP Server? +

The PromptingBox MCP Server server has 14 write tools including add_context_source, add_tags, create_folder. 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 PromptingBox MCP Server.

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

29 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 18 can modify, create, or delete data.

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

Register the PromptingBox 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 PromptingBox MCP Server tool call.

Deterministic rules across all 29 PromptingBox MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

29 PromptingBox 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.