이 모델 컨텍스트 프로토콜(MCP) 서버는 JSON 템플릿에 따라 텍스트에서 데이터를 구조화하고 추출하기 위한 도구를 제공합니다.
자리 표시자를 사용하여 JSON 템플릿을 기반으로 텍스트 그룹화 및 구조화
AI가 생성한 텍스트에서 정보를 추출하여 구조화된 JSON 형식으로 변환
중첩된 플레이스홀더를 사용한 임의의 JSON 구조 지원
텍스트에서 키-값 쌍의 지능적 추출
다운스트림 애플리케이션을 위한 구조화된 데이터로 프로세스 AI 출력
Related MCP server: Unstructured Document Processor MCP
지엑스피1
npm start핫 리로딩을 통한 개발의 경우:
npm run dev:watch이 MCP 서버는 두 가지 주요 도구를 제공합니다.
group-text-by-json )이 도구는 플레이스홀더가 포함된 JSON 템플릿을 사용하여 AI가 템플릿의 구조에 따라 텍스트를 그룹화하도록 프롬프트를 생성합니다.
{
"template": "{ \"type\": \"<type>\", \"text\": \"<text>\" }"
}이 도구는 템플릿을 분석하고, 플레이스홀더 키를 추출하고, AI가 키-값 형식으로 정보를 추출하도록 안내하는 프롬프트를 반환합니다.
text-to-json )이 도구는 이전 단계에서 그룹화된 텍스트 출력을 가져와 원래 템플릿을 기반으로 구조화된 JSON 개체로 변환합니다.
{
"template": "{ \"type\": \"<type>\", \"text\": \"<text>\" }",
"text": "type: pen\ntext: This is a blue pen"
}텍스트에서 키-값 쌍을 추출하고 템플릿에 따라 구조화합니다.
플레이스홀더를 사용하여 JSON 템플릿을 정의합니다.
{
"item": {
"name": "<name>",
"price": "<price>",
"description": "<description>"
}
}group-text-by-json 사용하여 AI에 대한 프롬프트를 만듭니다.
이 도구는 이름, 가격, 설명 등의 플레이스홀더 키를 식별합니다.
이러한 키로 정보를 그룹화하도록 AI에 지시하는 프롬프트를 생성합니다.
AI 모델에 프롬프트를 보내고 그룹화된 텍스트를 받습니다.
name: Blue Pen
price: $2.99
description: A smooth-writing ballpoint pen with blue inktext-to-json 사용하여 그룹화된 텍스트를 JSON으로 변환합니다.
결과: GXP8
템플릿에는 유효한 JSON 구조 내의 어느 곳에나 플레이스홀더가 포함될 수 있습니다.
자리 표시자를 정의하려면 꺾쇠괄호를 사용합니다: <name> , <type> , <price> 등.
템플릿은 유효한 JSON 문자열이어야 합니다.
플레이스홀더는 모든 중첩 수준에 있을 수 있습니다.
복잡한 중첩 구조 지원
중첩된 플레이스홀더가 있는 템플릿 예:
{
"product": {
"details": {
"name": "<name>",
"category": "<category>"
},
"pricing": {
"amount": "<price>",
"currency": "USD"
}
},
"metadata": {
"timestamp": "2023-09-01T12:00:00Z"
}
}서버는 다음과 같이 작동합니다.
JSON 템플릿을 분석하여 플레이스홀더 키 추출
이러한 키로 정보를 추출하도록 AI 모델을 안내하는 프롬프트 생성
AI가 생성한 텍스트를 구문 분석하여 키-값 쌍 추출
원래 템플릿 구조를 기반으로 JSON 객체 재구성
Node.js v18 이상
npm 또는 yarn
# Install dependencies
npm install
# Build the project
npm run build
# Run the server
npm start
# Development with hot reloading
npm run dev:watch이 프로젝트에는 다음이 결합된 맞춤형 핫 리로딩 설정이 포함되어 있습니다.
nodemon : src 디렉토리의 파일 변경 사항을 감시하고 TypeScript 파일을 다시 빌드합니다.
browser-sync : 빌드 파일이 변경되면 브라우저를 자동으로 새로 고칩니다.
동시 실행 : 출력 동기화를 통해 두 서비스를 동시에 실행합니다.
설정은 다음과 같이 구성됩니다.
nodemon.json : TypeScript 감시 및 재구축을 제어합니다.
package.json : nodemon과 browser-sync를 동시에 실행하기 위해 사용합니다.
사용자 정의 핫 리로딩 기능을 사용하려면:
npm run dev:watch이렇게 하면 다음과 같은 개발 환경이 생성됩니다.
TypeScript 파일은 변경 시 자동으로 다시 빌드됩니다.
MCP 서버가 업데이트된 코드로 다시 시작됩니다.
연결된 브라우저가 새로 고쳐져 최신 변경 사항이 표시됩니다.
디버깅을 위해 MCP Inspector를 사용할 수 있습니다.
npm run dev이는 요청과 응답의 시각적 디버깅을 위해 MCP Inspector로 서버를 실행합니다.
Gives a prompt text for AI to group text based on JSON placeholders. This tool accepts a JSON template with placeholders.
| Name | Required | Description | Default |
|---|---|---|---|
| template | Yes | JSON template with placeholders |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool 'gives a prompt text' but does not explain what happens next—e.g., whether it returns a prompt for AI processing, requires additional steps, or has any side effects like rate limits or authentication needs. This leaves key behavioral traits unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences that directly address the tool's function and input. It avoids unnecessary details and is front-loaded with the core purpose. However, it could be more structured by explicitly separating usage guidelines or behavioral context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It does not explain what the tool returns (e.g., the prompt text format or any output structure), nor does it cover behavioral aspects like error handling or prerequisites. For a tool with no structured support, the description should provide more context to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal meaning beyond the input schema, which has 100% coverage for the single parameter 'template.' It restates that the tool 'accepts a JSON template with placeholders,' mirroring the schema's description. Since schema coverage is high, the baseline score is 3, as the description does not significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool 'gives a prompt text for AI to group text based on JSON placeholders,' which provides a vague purpose. It mentions the action ('gives a prompt text') and resource ('JSON placeholders'), but lacks specificity about what 'group text' means or how the prompt is used. It does not clearly distinguish from sibling tool 'text-to-json,' leaving ambiguity in its exact function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no guidance on when to use this tool versus alternatives. It does not mention the sibling tool 'text-to-json' or provide context for choosing between them. Without explicit usage instructions or exclusions, users must infer when this tool is appropriate, leading to potential misuse.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Converts groupped text from group-text-by-json tool to JSON. This tool accepts a JSON template with placeholders and groupped text from group-text-by-json tool.
| Name | Required | Description | Default |
|---|---|---|---|
| template | Yes | JSON template with placeholders | |
| text | Yes | Groupped text from groupTextByJson tool |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the conversion process but lacks details on error handling, output format, or any constraints (e.g., template syntax, validation rules). For a tool with no annotations, this leaves significant gaps in understanding how it behaves beyond the basic operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences that directly state the tool's function and inputs. It avoids unnecessary words and is front-loaded with the core purpose. However, the repetition of 'group-text-by-json tool' could be slightly streamlined, and it lacks structural elements like bullet points for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (data transformation with two parameters), lack of annotations, and no output schema, the description is incomplete. It covers the basic operation but misses details on output format, error cases, or example usage. While it mentions the sibling tool, more context on the overall workflow would improve completeness for effective agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters ('template' and 'text') with clear descriptions. The description adds minimal value by repeating that it accepts a 'JSON template with placeholders' and 'groupped text from groupTextByJson tool', but doesn't provide additional semantics beyond what the schema states. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: converting grouped text to JSON using a template. It specifies the verb 'converts' and the resource 'groupped text from group-text-by-json tool', making the action and input source explicit. However, it doesn't fully distinguish from its sibling 'group-text-by-json' beyond mentioning it as the source, missing an opportunity to clarify the workflow relationship more distinctly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by specifying that it accepts input from 'group-text-by-json tool', suggesting a sequential workflow. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., direct JSON creation tools) or any prerequisites beyond having the grouped text. No exclusions or clear when-not-to-use scenarios are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0group-text-by-jsontext-to-jsonScored across 2 tools
The two tools have clearly distinct purposes: group-text-by-json prepares text for grouping based on a JSON template, while text-to-json converts that grouped text into JSON. There is no overlap or ambiguity between them, as they represent sequential steps in a workflow.
Both tools follow a consistent verb-noun pattern with hyphens (group-text-by-json and text-to-json), clearly indicating their actions and targets. The naming is predictable and readable across the set.
With only 2 tools, the server feels thin for its apparent purpose of custom context management. This minimal set may limit functionality and require agents to work around gaps, as typical context-related operations might include more than just grouping and conversion.
The tool surface is severely incomplete for a custom context server. It lacks core operations such as creating, updating, deleting, or retrieving context entries, and only covers a narrow text-to-JSON conversion workflow, leaving significant gaps that will likely cause agent failures.
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
