json-promptor-mcp
json-promptor-mcp
一个通过启发式关键词提取将原始文本提示转换为结构化 JSON 提示的 MCP 服务器——无需 API 密钥。
工具
convert_prompt_to_json
接收原始文本提示并返回一个包含提取字段的结构化 JSON 对象:
purpose— 提示旨在实现的目标goal— 具体期望的结果audience— 输出的对象context— 背景信息或约束条件tone— 期望的语气/风格(正式、随意、技术性等)instructions— 提示中发现的分步说明format— 期望的输出格式(列表、段落、代码等)original_prompt— 原样保留的原始输入
edit_prompt_json
接收现有的结构化 JSON 提示、字段名称和新值。返回更新后的 JSON。
Related MCP server: simple-prompts-mcp
构建
npm install
npm run buildKiro 的 MCP 配置
添加到你的 mcp.json 中:
{
"mcpServers": {
"json-promptor": {
"command": "node",
"args": ["json-promptor-mcp/dist/index.js"]
}
}
}示例
输入提示:
写一篇面向开发者的正式博客文章,解释如何使用 Docker,以编号列表形式呈现。
输出:
{
"purpose": "write a formal blog post for developers explaining how to use docker, as a numbered list",
"goal": "",
"audience": "developers",
"context": "",
"tone": "formal",
"instructions": "",
"format": "numbered list",
"original_prompt": "Write a formal blog post for developers explaining how to use Docker, as a numbered list."
}Available Tools
2 toolsconvert_prompt_to_jsonA
Convert a raw text prompt into a structured JSON prompt with extracted fields (purpose, goal, audience, context, tone, instructions, format)
Inputs: prompt (required).
edit_prompt_jsonB
Edit a field in an existing structured JSON prompt
Inputs: structured_prompt (required), field (required), value (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools are clearly distinct: one converts raw text to a structured JSON prompt, the other edits an existing JSON prompt. There is no ambiguity or overlap.
Both tools follow the verb_noun pattern consistently: convert_prompt_to_json and edit_prompt_json. The naming is clear and predictable.
With only 2 tools, the server is minimal but appropriately scoped for its narrow purpose of converting and editing JSON prompts. However, it could benefit from a few more tools like validation.
The tools cover the core workflow of converting raw prompts to JSON and editing them. Missing operations like validation or export are minor gaps but do not severely hinder the stated purpose.
Related MCP Connectors
MCP server for generating rough-draft project plans from natural-language prompts.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for AI dialogue using various LLM models via AceDataCloud
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that uses Claude 3.5 Sonnet to transform ordinary prompts into structured, professionally engineered instructions for any LLM. It enhances AI interactions by adding context, requirements, and structural clarity to raw user inputs.13MIT
- AlicenseNot gradedqualityDmaintenanceA simple MCP server for utilizing prompts defined in YAML files.MIT
- AlicenseNot gradedqualityDmaintenanceConfigurable MCP server that lets you define LLM-powered tools via JSON, enabling easy integration of multiple models (GPT, Gemini, Claude, etc.) as MCP tools without writing Python code.6MIT
- AlicenseAqualityCmaintenanceLocal MCP server that uses a local Ollama model to rewrite rough prompt drafts into structured, optimized prompts for paid APIs, saving tokens and improving output quality.529 npmMIT