DeerPrompt

DeerPrompt is a VSCode extension, designed to let you develop and debug prompts in VSCode.

Features

• Multi-turn Conversations - debug complex prompt chains
• Function Calling - test tool integrations
• MCP - connect to external tools
• Token Counting - see what you're actually spending

Quick Start

DeerPrompt will automatically open its panel whenever you open a .md file, then you can start developing your prompts right inside it.

Configuration

Before you get started, you’ll need to configure your LLM providers and models.

LLM Providers and models

Works with any OpenAI-compatible API. Built-in presets for OpenAI, Anthropic, DeepSeek, Doubao, etc.

MCP Servers (Optional)

Standard MCP

Add local tools via MCP

Here's an example about how to add a local Python function as a DeerPrompt MCP tool.

1. Convert langchain's tool with FastMCP.

   # tools.py
   from mcp.server.fastmcp import FastMCP
   from langchain_core.tools import tool
   from langchain_mcp_adapters.tools import to_fastmcp
   
   @tool(description="Say hello to the user")
   def hello(name: str) -> str:
       return f"Hello, {name}!"
   
   mcp = FastMCP("Demo", tools=[to_fastmcp(hello)])
   
   if __name__ == "__main__":
       mcp.run()
   

2. Add to DeerPrompt MCP config: uv run tools.py