TypeScript MCP Server Boilerplate
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| greetA | 이름과 언어를 입력하면 인사말을 반환합니다. |
| calcA | 두 숫자와 연산자(+,-,*,/)를 입력받아 사칙연산 결과를 반환합니다. |
| timeA | 현재 시간을 반환합니다. |
| geocodeA | 도시 이름이나 주소를 입력받아 위도·경도 좌표를 반환합니다. (Nominatim OpenStreetMap API 사용) |
| get-weatherA | 위도·경도와 예보 기간을 입력받아 현재 날씨와 일별 예보를 반환합니다. (Open-Meteo API 사용, API 키 불필요) |
| generate-imageA | HuggingFace Inference API를 사용해 텍스트 프롬프트로 이미지를 생성합니다. (모델: black-forest-labs/FLUX.1-schnell, 환경변수 HF_TOKEN 필요) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| code-review | 코드와 언어를 입력받아 품질·버그·성능·모범 사례 관점에서 리뷰를 요청하는 프롬프트를 생성합니다. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| server-info | 서버 이름, 버전, 등록된 툴 목록, 시작 시각을 반환합니다. |
| server-status | 현재 시각, 프로세스 업타임, Node.js 버전, 메모리 사용량을 반환합니다. |
TDQS
Scored across 6 tools
Each tool serves a completely distinct purpose (arithmetic, image generation, geocoding, weather, greetings, time). There is no functional overlap between tools, making selection unambiguous.
Mixed conventions: 'generate-image' and 'get-weather' use kebab-case verb-noun patterns, while 'calc', 'geocode', 'greet', and 'time' use single lowercase words (with 'time' being a noun rather than a verb). Readable but inconsistent structure.
Six tools is reasonable for a boilerplate/demo server intended to showcase different integration patterns (HuggingFace, OpenStreetMap, Open-Meteo, simple functions). Not overwhelming, though the selection feels somewhat arbitrary.
No coherent domain unifies the tools; they appear to be random unrelated examples. While geocode+get-weather form a minimal workflow, the set lacks completeness for any specific purpose (weather, math, image gen, etc.) and appears as a disconnected grab bag of capabilities.