prompt-library-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_promptsA | Search the prompt library by keyword or category. Find tested, community-rated prompts for any task. Args: query: Search term (e.g. "code review", "security", "data") category: Filter by category (optional: development, business, data-science, security) |
| get_promptA | Get a specific prompt by ID, ready to use. Returns the full prompt text and metadata. Args: prompt_id: Prompt ID (from search_prompts) |
| share_promptA | Share a prompt with the community. Add a tested prompt or config to the library for others to use. Args: prompt_id: Unique ID (e.g. "my-code-review") title: Display title prompt_text: The full prompt text description: What this prompt does (1-2 sentences) category: Category (development, business, data-science, security, general) tags: JSON array of tags (e.g. '["python", "testing"]') author: Your name |
| rate_promptA | Rate a prompt — upvote if it worked well, downvote if not. Helps the community find the best prompts. Args: prompt_id: Prompt ID to rate upvote: True = thumbs up, False = thumbs down |
| list_popular_promptsA | List the most popular prompts by usage and votes. Args: limit: Max results (default: 10) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct action: get by ID, list popular, rate, search, and share. No functional overlap.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., get_prompt, share_prompt).
5 tools cover the essential operations for a prompt library without being excessive or insufficient.
Core CRUD-like operations are present (read, list, search, create, rate). Missing update/delete for prompts, but the surface covers primary use cases.