PluginBench
MCP Server
Maintained

prompts.chat MCP Server MCP Server

io.github.f/prompts.chat-mcp

Search and retrieve thousands of AI prompts from prompts.chat directly in your coding assistant.

What is the prompts.chat MCP Server MCP server?

The prompts.chat MCP Server provides access to thousands of AI prompts from the prompts.chat social platform. It enables searching, retrieving, and saving prompts with support for variable substitution, allowing you to integrate curated AI prompts directly into your workflow.

This server connects your AI coding assistant to prompts.chat, a social platform for sharing AI prompts. You can search for prompts by keyword, category, or tag, retrieve specific prompts by ID, and save new prompts to your account. It's useful for quickly finding and applying well-crafted prompts for common tasks like code review, system role-playing, and specialized workflows.

How to install prompts.chat MCP Server

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • PROMPTS_API_KEY
    secret

    API key for authenticated requests (enables save_prompt tool)

  • PROMPTS_QUERY

    Query string to filter prompts (e.g., users=a,b&categories=c,d&tags=e,f)

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "prompts-chat-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@fkadev/prompts.chat-mcp"
      ],
      "env": {
        "PROMPTS_API_KEY": "<YOUR_PROMPTS_API_KEY>",
        "PROMPTS_QUERY": "<YOUR_PROMPTS_QUERY>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • search_prompts — Search for AI prompts by keyword with support for filtering by type, category, and tag.
  • get_prompt — Retrieve a prompt by ID with automatic variable elicitation for prompts containing template variables.
  • save_prompt — Save a new prompt to your account (requires PROMPTS_API_KEY).

Use cases

  • Find and use specialized prompts for code review, debugging, and documentation
  • Search for role-playing prompts like 'act as a Linux terminal' or domain-specific assistants
  • Discover productivity and writing prompts curated by the prompts.chat community
  • Save and organize your own custom prompts for reuse across projects
  • Integrate community-vetted prompts into your AI coding workflow without manual copying

prompts.chat MCP Server MCP server FAQ

What is the prompts.chat MCP Server?

It's an MCP server that connects your AI coding assistant to prompts.chat, a social platform with thousands of AI prompts. You can search, retrieve, and save prompts directly in Cursor, Claude, VS Code, and other MCP-compatible clients.

Is it free to use?

Yes, searching and retrieving public prompts is free. Saving prompts to your account requires a PROMPTS_API_KEY, which you can obtain by signing up at prompts.chat.

How do I install it in Cursor?

Add this to ~/.cursor/mcp.json: {"mcpServers": {"prompts-chat": {"url": "https://prompts.chat/api/mcp"}}} (remote) or use the local npx command with @fkadev/prompts.chat-mcp.

Can I use prompts with variables?

Yes, prompts with ${variable} syntax are automatically handled. The server supports variable elicitation when you retrieve a prompt.

What are the system requirements?

Node.js >= v18.0.0 is required for local installation. The remote server option (https://prompts.chat/api/mcp) works without local setup.

Which clients are supported?

Cursor, Windsurf, VS Code, Claude Code, and Zed are all supported with configuration examples provided in the README.

README (reference)

Source of truth, from the repository.

<p align="center"> <img src="https://prompts.chat/logo.svg" alt="prompts.chat" width="200" /> </p> <h1 align="center">prompts.chat MCP Server</h1> <p align="center"> Access thousands of AI prompts directly in your AI coding assistant </p> <p align="center"> <a href="https://prompts.chat"><img src="https://img.shields.io/badge/Website-prompts.chat-blue" alt="Website"></a> <a href="https://www.npmjs.com/package/@fkadev/prompts.chat-mcp"><img src="https://img.shields.io/npm/v/@fkadev/prompts.chat-mcp?color=red" alt="NPM Version"></a> <a href="./LICENSE"><img src="https://img.shields.io/npm/l/@fkadev/prompts.chat-mcp" alt="License"></a> </p>

Features

  • MCP Prompts - Browse and use prompts directly via MCP prompts capability
  • Search Prompts - Search for AI prompts by keyword, category, or tag
  • Get Prompt - Retrieve prompt details by ID with variable substitution
  • Variable Support - Prompts with ${variable} syntax are automatically handled

🛠️ Installation

Requirements

  • Node.js >= v18.0.0
  • An MCP-compatible client (Cursor, Windsurf, VS Code, Claude Code, etc.)
<details> <summary><b>Install in Cursor</b></summary>

Add this to your Cursor MCP config file (~/.cursor/mcp.json):

Remote Server (Recommended)

{
  "mcpServers": {
    "prompts-chat": {
      "url": "https://prompts.chat/api/mcp"
    }
  }
}

Local Server

{
  "mcpServers": {
    "prompts-chat": {
      "command": "npx",
      "args": ["-y", "@fkadev/prompts.chat-mcp"]
    }
  }
}
</details> <details> <summary><b>Install in Windsurf</b></summary>

Add this to your Windsurf MCP config file:

Remote Server (Recommended)

{
  "mcpServers": {
    "prompts-chat": {
      "serverUrl": "https://prompts.chat/api/mcp"
    }
  }
}

Local Server

{
  "mcpServers": {
    "prompts-chat": {
      "command": "npx",
      "args": ["-y", "@fkadev/prompts.chat-mcp"]
    }
  }
}
</details> <details> <summary><b>Install in VS Code</b></summary>

Add this to your VS Code MCP settings:

Remote Server (Recommended)

"mcp": {
  "servers": {
    "prompts-chat": {
      "type": "http",
      "url": "https://prompts.chat/api/mcp"
    }
  }
}

Local Server

"mcp": {
  "servers": {
    "prompts-chat": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@fkadev/prompts.chat-mcp"]
    }
  }
}
</details> <details> <summary><b>Install in Claude Code</b></summary>

Remote Server (Recommended)

claude mcp add --transport http prompts-chat https://prompts.chat/api/mcp

Local Server

claude mcp add prompts-chat -- npx -y @fkadev/prompts.chat-mcp
</details> <details> <summary><b>Install in Zed</b></summary>

Add this to your Zed settings.json:

{
  "context_servers": {
    "prompts-chat": {
      "command": {
        "path": "npx",
        "args": ["-y", "@fkadev/prompts.chat-mcp"]
      }
    }
  }
}
</details>

⚙️ Configuration

The local server supports the following environment variables:

VariableDescription
PROMPTS_API_KEYOptional API key for authenticated requests
PROMPTS_QUERYOptional query string to filter prompts (e.g., users=a,b&categories=c,d&tags=e,f)

Example with Environment Variables

{
  "mcpServers": {
    "prompts-chat": {
      "command": "npx",
      "args": ["-y", "@fkadev/prompts.chat-mcp"],
      "env": {
        "PROMPTS_API_KEY": "your-api-key",
        "PROMPTS_QUERY": "users=username&categories=coding&tags=productivity"
      }
    }
  }
}

🔨 Available Tools

ToolDescription
search_promptsSearch for AI prompts by keyword. Supports filtering by type, category, and tag.
get_promptGet a prompt by ID. Supports variable elicitation for prompts with template variables.
save_promptSave a new prompt to your account. Requires PROMPTS_API_KEY.

📚 MCP Prompts

This server exposes all public prompts from prompts.chat as MCP prompts. Use prompts/list to browse available prompts and prompts/get to retrieve them with variable substitution.

📖 Example Usage

Ask your AI assistant:

Search for prompts about code review
Get the prompt for "act as a linux terminal"

🔗 Links

📄 License

ISC

Related MCP servers

Bug reports, AI diagnosis, and status management for Cursor, Claude, Windsurf.

View repository →

Bidirectional data lineage graph for Power BI (.pbix) files, from source to display

0
Python
View repository →

Bidirectional data lineage graph for Power BI (.pbix) files, from source to display

0
Python
View repository →
NUNuzo Memory logo

Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.

2
TypeScript
Apache-2.0
View repository →

AI-powered i18n translation management for Nuxt projects—find missing keys, remove dead ones, rename across locales.

11
TypeScript
MIT
View repository →

Inspect, validate and surgically edit Tiled map files (.tmx/.tmj) — byte-preserving, 12 tools.