// MCP TOOL REFERENCE

PROMPT REGISTRY MCP TOOLS

7 tools from the Prompt Registry MCP MCP Server, categorised by risk level.

// ALL 7 PROMPT REGISTRY MCP TOOLS

READ 2 tools

Read filter_prompts_by_tags Lists active prompts (project-specific or user global defaults) that match all specified tags. Read get_prompt_file_content Retrieves the raw JSON definition of the active prompt (project-specific or user global default).

WRITE 4 tools

Write load_default_prompts Loads all default prompts from the default_prompts_data directory into the active prompt directory, skippin... Write add_prompt Adds a new prompt to the project-specific prompt directory. Write refine_and_add_prompt Optimizes a prompt using Claude Prompt Optimizer techniques, then adds the refined version to the registry. Write update_prompt Updates an existing prompt. Updates are always written to the project-specific directory, creating an overr...

DESTRUCTIVE 1 tools

Destructive delete_prompt Deletes a prompt from the project-specific directory. If a user global default with the same ID exists, it ...

// FAQ

How many tools does the Prompt Registry MCP MCP server have? +

The Prompt Registry MCP MCP server exposes 7 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Prompt Registry MCP tools? +

Route the Prompt Registry MCP server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Prompt Registry MCP tools fall into? +

Prompt Registry MCP tools are categorised as Read (2), Write (4), Destructive (1). Each category has a recommended default policy.

Enforce policy on every Prompt Registry MCP tool call.

Start from Prompt Registry MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.