# prompts.chat MCP server

> Search, fetch, improve and save AI prompts and Agent Skills from the prompts.chat community library.

- Listing: https://mcp.tc/i/prompts-chat
- Connect: use the server's own URL `https://prompts.chat/api/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: f (Fatih Kadir Akın)
- Repository: <https://github.com/f/prompts.chat-mcp>
- Package: npm `@fkadev/prompts.chat-mcp`

## About

Connects to prompts.chat, a social platform for sharing AI prompts. You can search prompts by keyword, category, tag or type, fetch a prompt by ID and fill in its template variables, and rewrite a basic prompt into a more structured one. It also handles Agent Skills: search them, download their files, and create or edit skills in your account.

Runs as a hosted streamable-http endpoint at https://prompts.chat/api/mcp, or locally with npx using the @fkadev/prompts.chat-mcp package. Searching and reading need no sign-in. Saving prompts and skills requires a prompts.chat API key. The server also exposes public prompts as MCP prompts.

## What it can do

- Search prompts by keyword, type, category or tag
- Get a prompt by ID and fill in its template variables
- Improve a basic prompt for text, image, video or sound output
- Save new prompts to your prompts.chat account
- Search and download Agent Skills with their files
- Create skills and add, update or remove skill files

## Tools (10)

- `search_prompts`: Search prompts by keyword with optional type, category and tag filters.
- `get_prompt`: Get a prompt by ID and optionally fill in its template variables.
- `save_prompt`: Save a new prompt to your prompts.chat account.
- `improve_prompt`: Turn a basic prompt into a structured one, in text, image, video or sound form.
- `save_skill`: Save a new multi-file Agent Skill to your account.
- `add_file_to_skill`: Add a reference doc, script or config file to a skill you own.
- `update_skill_file`: Update an existing file in an Agent Skill, including SKILL.md.
- `remove_file_from_skill`: Remove a file from a skill.
- `get_skill`: Get an Agent Skill by ID with its metadata and all file contents.
- `search_skills`: Search Agent Skills by keyword, category or tag.

## Example prompts

- "Search prompts.chat for code review prompts"
- "Get the prompt for "act as a linux terminal" and fill in its variables"
- "Improve this prompt for an image generator: a lighthouse in a storm"
- "Find Agent Skills for database migration review"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

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

2. Start Claude Code and type `/mcp`. **prompts-chat** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

2. Name it **prompts.chat** and paste this URL:

```url
https://prompts.chat/api/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=prompts.chat&connectorUrl=https%3A%2F%2Fprompts.chat%2Fapi%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://prompts.chat/api/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://prompts.chat/api/mcp` as the server URL and choose **No authentication**.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=prompts-chat&config=eyJ1cmwiOiJodHRwczovL3Byb21wdHMuY2hhdC9hcGkvbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

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

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=prompts-chat&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fprompts.chat%2Fapi%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"prompts-chat","type":"http","url":"https://prompts.chat/api/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

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

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

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

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add prompts-chat --url https://prompts.chat/api/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.prompts-chat]
url = "https://prompts.chat/api/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http prompts-chat https://prompts.chat/api/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

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

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://prompts.chat/api/mcp`.

## Details

- Server version: 1.0.0
- MCP protocol version: 2025-11-25
- Last checked: 2026-10-04 (reachable)
- Listed: 2026-10-04
- Updated: 2026-10-04

---
Source: https://mcp.tc/i/prompts-chat (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
