stdict-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_PATH_TOKEN | No | Cloudflare Workers 배포 시 MCP 경로에 포함되는 임의의 보안 토큰 | |
| KOREAN_DICT_API_KEY | Yes | 국립국어원 표준국어대사전 Open API 인증 키 |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_dictionaryB | 국립국어원 표준국어대사전에서 표제어와 뜻풀이를 검색합니다. |
| get_dictionary_entryA | 표제어나 검색 결과의 targetCode로 상세 뜻풀이, 품사, 용례를 조회합니다. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools target clearly different steps of a lookup workflow: search_dictionary finds headwords, while get_dictionary_entry retrieves full detail by headword or targetCode. There is no plausible way to confuse them, and the descriptions reinforce the dependency order.
Both names use a consistent snake_case verb_noun pattern (search_/get_ + dictionary resource). The convention is predictable and readable.
Two tools is on the thin side, though the search-then-retrieve pair is exactly the minimum needed for a lookup service. A small amount of additional surface (e.g. suggestions or sense listing) would make it feel less minimal.
The read-only lifecycle is fully covered: search to find headwords, then fetch definitions, parts of speech, and usage examples. Gaps are minor for a dictionary API (no fuzzy/spelling-suggestion or thesaurus navigation), and agents can work around them by re-searching.