// SCAN REPORT

MCP Prompt Manager

33 tools. 11 can modify or destroy data without limits.

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

Last updated: 12 Jun 2026

11 can modify or destroy data

22 read-only

33 tools total

Community server · catalogue entry verified 12/06/2026

How to control MCP Prompt Manager ↓

TOOL MAP

What MCP Prompt Manager exposes to your agents

Read (22) Write / Execute (10) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Prompt Manager tools

Destructive · High delete-prompt This tool permanently deletes prompt files without the ability to recover them (barring external backup systems). Execute · Medium process-template Processing a template with 'advanced logic' suggests the tool evaluates and runs logic (conditionals, loops, variable substitution, or embedded code) rather than merely reading or writing static data. Write · Low favorite-prompt This tool modifies metadata (favorite status) of an existing prompt. Write · Medium categorize-prompt This is a Write operation because it creates or modifies data reversibly.

11 of MCP Prompt Manager's 33 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Prompt Manager

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

Deny destructive operations

{
  "delete-prompt": {
    "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

{
  "favorite-prompt": {
    "limits": [
      {
        "counter": "favorite-prompt_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "compare-prompt-versions": {
    "limits": [
      {
        "counter": "compare-prompt-versions_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 MCP Prompt Manager — 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 MCP PROMPT MANAGER →

Free to start. No card required.

FULL CATALOGUE

All 33 MCP Prompt Manager tools

DESTRUCTIVE 1 tools

Destructive delete-prompt Delete a prompt file

EXECUTE 1 tools

Execute process-template Process a prompt template with advanced logic

WRITE 9 tools

Write favorite-prompt Add or remove a prompt from favorites Write rollback-prompt Rollback a prompt to a specific version Write categorize-prompt Set category for a prompt Write create-prompt Create a new prompt file Write create-prompt-from-template Create a new prompt file from a template with variables Write export-prompts Export prompts to JSON format for backup or sharing Write import-prompts Import prompts from JSON format Write tag-prompt Add tags to a prompt Write update-prompt Update an existing prompt file

READ 22 tools

Read compare-prompt-versions Compare two versions of a prompt and show differences Read get-cache-stats Read cache statistics for files/metadata/search/templates Read get-import-export-status Get import/export system status and capabilities Read get-policy-status Get current policy/permission flags Read get-popular-templates Get most popular templates from the library Read get-prompt Get the content of a specific prompt Read get-prompt-version Get the content of a specific version of a prompt Read get-prompt-version-stats Get statistics about a prompt Read get-rate-limit-status Get current rate limiter stats (standard/strict/upload) Read get-server-stats Get process and server runtime stats Read get-template-details Get detailed information about a specific template Read list-by-category List prompts by category Read list-favorites List all favorite prompts Read list-prompt-versions List all versions of a specific prompt Read list-prompts List all available prompts with metadata Read list-template-categories List all available template categories in the template library Read list-template-variables List all variables in a template prompt Read list-templates-by-category List all templates in a specific category Read read-prompt Read a specific prompt file Read render-template Render a template with provided variables Read search-prompts Search prompts by filename or content with intelligent fuzzy matching Read search-templates Search templates in the template library

EXPLORE

Related servers

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

FAQ

Questions about MCP Prompt Manager

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

Yes. The MCP Prompt Manager server exposes 1 destructive tools including delete-prompt. 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 Prompt Manager? +

The MCP Prompt Manager server has 9 write tools including favorite-prompt, rollback-prompt, categorize-prompt. 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 Prompt Manager.

How many tools does the MCP Prompt Manager MCP server expose? +

33 tools across 3 categories: Destructive, Read, Write. 22 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on MCP Prompt Manager? +

Register the MCP Prompt Manager 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 Prompt Manager tool call.

Deterministic rules across all 33 MCP Prompt Manager tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP PROMPT MANAGER →

Free to start. No card required.

33 MCP Prompt Manager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.