mcpField
V
veprompts-mcp-server

veprompts-mcp-server

Local
github.com/VeduisAI & Agents0Updated 6d ago
Repository

About veprompts-mcp-server

veprompts-mcp-server exposes the VePrompts library to AI clients, covering prompts, MCP servers, skills, frameworks, and AI model pricing. It offers searchable entries and read-only datasets without requiring API keys.

Key features

  1. 01Fuzzy search across library entries
  2. 02Look up current AI model pricing
  3. 03Retrieve prompts, servers, and skills
  4. 04Compare entities and retrieve frameworks
  5. 05Look up glossary definitions
  6. 06Read-only library and pricing resources

Use cases

  1. 01Find prompts, guides, tools, or MCP servers
  2. 02Check tracked model input and output pricing
  3. 03Retrieve an MCP server's install and tool details
  4. 04Fetch skill instructions or framework profiles

MCP support

It provides eight tools and three read-only resources to MCP clients, including the library index, pricing dataset, and MCP server directory.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "veduis-veprompts": {
      "command": "npx",
      "args": [
        "-y",
        "veprompts-mcp-server"
      ]
    }
  }
}
Run commandnpx -y veprompts-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmveprompts-mcp-server1.1.2

Tools

8

Saved tool list · updated 5d ago

ParameterTypeRequiredDescription
limitintegerNoMaximum number of results to return.
querystringYesSearch query matched against prompt titles, descriptions, and tags.

Details

From the project README

VePrompts MCP Server

npm version License: MIT DOI PyPI

Official Model Context Protocol (MCP) server that exposes the VePrompts library to AI clients such as Claude Desktop, Cursor, VS Code, and Cline. It provides eight tools and three read-only resources:

Tools
  • veprompts_search - Fuzzy search across the VePrompts library (prompts, guides, tools, MCP servers) using titles, descriptions, and tags.
  • veprompts_pricing_lookup - Query real-time API pricing (input/output per 1M tokens) for 400+ AI models tracked by VePrompts.
  • veprompts_get_prompt - Fetch a prompt by slug, returning its full frontmatter metadata and raw prompt template.
  • veprompts_get_mcp_server - Fetch an MCP server directory entry by slug: description, install command, exposed tools, and client compatibility.
  • veprompts_get_skill - Fetch an agent skill by slug: instructions plus bundled resource files.
  • veprompts_compare - Fetch a curated X-vs-Y comparison by slug or entity name: verdict, when to pick each option, and FAQs.
  • veprompts_get_framework - Fetch an agent framework profile by slug or name.
  • veprompts_get_glossary - Fetch a glossary term definition by slug or term.
Resources

Quickstart (npx)

Run directly without cloning:

npx -y veprompts-mcp-server

Client Configuration

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "veprompts": {
      "command": "npx",
      "args": ["-y", "veprompts-mcp-server"]
    }
  }
}
Cursor

Add to ~/.cursor/mcp.json (or via Settings > Features > MCP):

{
  "mcpServers": {
    "veprompts": {
      "command": "npx",
      "args": ["-y", "veprompts-mcp-server"]
    }
  }
}
VS Code

Add to your MCP settings:

{
  "servers": {
    "veprompts": {
      "command": "npx",
      "args": ["-y", "veprompts-mcp-server"]
    }
  }
}

No API keys or environment variables are required.

Local Development & Build

git clone https://github.com/Veduis/veprompts-mcp-server.git
cd veprompts-mcp-server
npm install
npm run build
node dist/index.js

Data Provenance & Ecosystem

License

MIT License. Copyright (c) 2026 Veduis LLC and VePrompts.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.