MCP Server
The PrompTick MCP Server lets AI coding assistants — Claude Code, Cursor, Windsurf, VS Code, JetBrains, Zed, and more — call PrompTick's prompt engineering tools directly from inside your editor.
What is MCP?
Model Context Protocol is an open standard that lets AI assistants talk to external tools through a well-defined interface. PrompTick hosts an MCP server you can connect to from any MCP-compatible client.
What you get
Three tools exposed over MCP:
| Tool | What it does |
|---|---|
generate_prompt | Create a new optimized AI prompt (system + user) from a use-case description |
improve_prompt | Enhance an existing AI prompt for clarity, structure, and effectiveness |
enrich_coding_prompt | Turn a coding task description into a rich, context-aware prompt for your coding assistant |
See Tools for input/output schemas and examples.
Why use it?
- Better prompts, zero context-switching. Your AI assistant can ask PrompTick to produce production-grade prompts without you leaving the editor.
- Smarter coding sessions.
enrich_coding_promptdoes automatic two-step context discovery — your assistant reads the files PrompTick asks for, then gets back a far better prompt to work from. - Consistent across clients. One MCP key works everywhere — the same PrompTick tools appear in every supported IDE.
Endpoint and transport
- Endpoint:
https://api.promptick.ai/api/mcp - Transport: Streamable HTTP (stateless)
- Auth:
Authorization: Bearer mk_live_<your-key> - Supports: progress notifications via SSE streaming
Supported clients
Claude Code, Cursor, VS Code, Windsurf, JetBrains, Zed, Cline, Continue, Roo Code, Cody, Augment, Gemini CLI, Amazon Q. Each has a client-specific config format — see the Clients pages.
Next steps
- Quickstart — connect in 3 minutes
- Tools reference
- Managing API keys