Search and retrieve AI prompts from prompts.chat, the social platform for AI prompts.
${variable} syntax are automatically handledAdd this to your Cursor MCP config file (~/.cursor/mcp.json):
{
"mcpServers": {
"prompts-chat": {
"url": "https://prompts.chat/api/mcp"
}
}
}
{
"mcpServers": {
"prompts-chat": {
"command": "npx",
"args": ["-y", "@fkadev/prompts.chat-mcp"]
}
}
}
Add this to your Windsurf MCP config file:
{
"mcpServers": {
"prompts-chat": {
"serverUrl": "https://prompts.chat/api/mcp"
}
}
}
{
"mcpServers": {
"prompts-chat": {
"command": "npx",
"args": ["-y", "@fkadev/prompts.chat-mcp"]
}
}
}
Add this to your VS Code MCP settings:
"mcp": {
"servers": {
"prompts-chat": {
"type": "http",
"url": "https://prompts.chat/api/mcp"
}
}
}
"mcp": {
"servers": {
"prompts-chat": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@fkadev/prompts.chat-mcp"]
}
}
}
claude mcp add --transport http prompts-chat https://prompts.chat/api/mcp
claude mcp add prompts-chat -- npx -y @fkadev/prompts.chat-mcp
Add this to your Zed settings.json:
{
"context_servers": {
"prompts-chat": {
"command": {
"path": "npx",
"args": ["-y", "@fkadev/prompts.chat-mcp"]
}
}
}
}
The local server supports the following environment variables:
| Variable | Description |
|---|---|
PROMPTS_API_KEY | Optional API key for authenticated requests |
PROMPTS_QUERY | Optional query string to filter prompts (e.g., users=a,b&categories=c,d&tags=e,f) |
{
"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"
}
}
}
}
| Tool | Description |
|---|---|
search_prompts | Search for AI prompts by keyword. Supports filtering by type, category, and tag. |
get_prompt | Get a prompt by ID. Supports variable elicitation for prompts with template variables. |
save_prompt | Save a new prompt to your account. Requires PROMPTS_API_KEY. |
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.
Ask your AI assistant:
Search for prompts about code review
Get the prompt for "act as a linux terminal"
ISC
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y @fkadev/prompts.chat-mcpMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-f-prompts-chat-mcp": {
"command": "npx",
"args": [
"-y",
"@fkadev/prompts.chat-mcp"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup reference@fkadev/prompts.chat-mcpnpmprompts.chat MCP Server works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.