promptsharp
Professional prompt library over remote MCP: 13 verticals, free discovery scope.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"promptsharp": {
"url": "https://promptsharp.ai/mcp"
}
}
}Remote endpoints
https://promptsharp.ai/mcpstreamable-httpWhat it can do
Tool inventory
Tools (3)
🟢search_prompts(query, vertical, section, limit)
Search the PromptSharp prompt library. Returns ready-to-run AI prompts scoped to your license tier (no token = 15 public teasers; vertical Pro = your vertical; all-access = the full cross-vertical library). Locked results are shown as stubs with an upgrade hint.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keywords to match against title, use-case, section, vertical, and prompt body."
},
"vertical": {
"type": "string",
"description": "Optional vertical slug filter, e.g. sales, marketing, finance, cpg, dev, product, csuite, consulting, career, personal_finance, law, air."
},
"section": {
"type": "string",
"description": "Optional section slug filter within a vertical."
},
"limit": {
"type": "integer",
"description": "Max results (1-25, default 10).",
"minimum": 1,
"maximum": 25
}
},
"required": [
"query"
]
}🟢get_prompt(id)
Fetch one prompt by id: the full copy-paste prompt plus its guardrails and a why-it-works note. Requires that the prompt is within your license scope.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Prompt id, e.g. pros-01 (from search_prompts results)."
}
},
"required": [
"id"
]
}🟢list_verticals
List every vertical in the PromptSharp library with its sections, prompt counts, and whether it is unlocked for your current license tier.
Input Schema
{
"type": "object",
"properties": {}
}Community
Evidence