네이버 API MCP 서버
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NAVER_CLIENT_ID | Yes | 네이버 클라이언트 아이디 (애플리케이션 등록 후 발급) | |
| NAVER_CLIENT_SECRET | Yes | 네이버 클라이언트 시크릿 (애플리케이션 등록 후 발급) |
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
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| naver-api-guide |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool has a unique, clearly identifiable purpose: search tools target different Naver services (blog, kin, shopping, encyclopedia), while trend tools are differentiated by resource (keyword vs category) and dimension (age, device, gender). No two tools appear to overlap in function.
Naming follows a predictable verb-noun-modifier pattern (search-<service> and get-<resource>-by-<dimension>/trends). However, there is a minor inconsistency between using 'search' for services and 'get' for trends, and the suffix 'trends' is not a dimension like 'by-age'. Overall still readable and systematic.
With 12 tools, the server is well-scoped, covering a typical Naver API surface without being bloated. Each tool earns its place, and the count is within the ideal range for a focused MCP server.
The tool set covers primary Naver search services and trend analytics across multiple dimensions. Minor gaps include missing search services (e.g., web, news, image) and no explicit overall trend endpoint separate from the by-dimension variants, but the core domain is well represented.