Skip to main content

Bareun — Korean NLP & Spell/Grammar Checking

ai.bareun/bareunVersion 3.0.0

Korean NLP MCP server: morphological analysis, tokenization, spell & grammar checking (Bareun)

Status

Responds356 msAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.
Last checked
Nov 14, 2026, 13:28 UTC
Latency
356 ms
Remotes responding
1 of 1
Sign-in
API key
Hosting
Hosted outside the EU (detected)
Registry data as of
Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP
https://api.bareun.ai/mcpResponds356 ms
No sign-in

Claude Code

claude mcp add --transport http bareun https://api.bareun.ai/mcp --header 'Authorization: Bearer <YOUR_TOKEN>'

Replace <YOUR_TOKEN> before running.

Claude Desktop and claude.ai

Settings > Connectors > Add custom connector
Name: bareun
Remote MCP server URL: https://api.bareun.ai/mcp
This server expects the header Authorization.

Cursor

{
  "mcpServers": {
    "bareun": {
      "url": "https://api.bareun.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Replace <YOUR_TOKEN> before running.

VS Code

code --add-mcp '{"name":"bareun","type":"http","url":"https://api.bareun.ai/mcp","headers":{"Authorization":"Bearer <YOUR_TOKEN>"}}'

Replace <YOUR_TOKEN> before running.

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

6 tools

Tools of Bareun — Korean NLP & Spell/Grammar Checking
Read-only
Idempotent
Open world
analyze_syntax한국어 문장의 형태소 분석을 수행합니다. 문장을 어절·형태소로 나누고 품사를 부착합니다. format=compact 면 '표층형/품사' 요약 문자열을, full 이면 전체 구조 JSON 을 돌려줍니다. with_sense=true 를 주면 동형이의어(같은 표기, 다른 뜻: 배[腹]/배[船]/배[梨])의 의미까지 구분해 어깨번호·뜻풀이를 함께 돌려줍니다(베타). EN: Performs morphological analysis of Korean text. Splits a sentence into words and morphemes and attaches part-of-speech tags. format=compact returns a short summary string of surface form/POS tag, and full returns the complete structure as JSON. with_sense=true also disambiguates homographs (same spelling, different meaning, such as 배 for belly, ship and pear) and returns the superscript number and definition (beta).NoYesNot declaredNo
analyze_syntax_raw후처리 없는 순수 형태소 분석을 수행합니다. 분절·품사 태깅 모델의 추론 결과를 그대로 반환하며 복합명사·복합동사 분해, 자동 띄어쓰기·붙여쓰기, 사용자 사전을 적용하지 않습니다. 모델 성능 평가나 말뭉치 재태깅처럼 후처리가 섞이지 않은 출력이 필요할 때만 쓰고, 일반적인 분석에는 analyze_syntax 를 쓰세요. with_sense=true 면 동형이의어 의미 구분(WSD, 베타) 결과도 후처리 없이 함께 돌려줍니다. EN: Performs raw morphological analysis without post-processing. Returns the segmentation and POS tagging model output as is, without compound noun or compound verb decomposition, automatic spacing or joining, or user dictionaries. Use it only when you need output free of post-processing, such as model evaluation or re-tagging a corpus, and use analyze_syntax for ordinary analysis. with_sense=true also returns word sense disambiguation (WSD, beta) without post-processing.NoYesNot declaredNo
correct_grammar한국어 문장의 맞춤법·띄어쓰기를 교정합니다. 교정된 문장과 교정 블록(원문/교정문) 목록을 돌려줍니다. 원문을 다시 쓰지 않고 어긋난 자리만 고치므로 글의 문체·말투가 그대로 남습니다. 고친 자리마다 근거가 되는 한글맞춤법 조항(예: 제1장 총칙 제2항)과 설명·예시가 함께 실려 오므로, 교열 근거를 대야 하는 일에 적합합니다. 띄어쓰기가 전혀 없는 음성 인식 결과·자동 자막 원고도 복원하고 문장 경계를 찾아 문장 부호를 넣습니다. EN: Corrects spelling and word spacing in Korean text. Returns the corrected sentence and a list of correction blocks (original/corrected). It fixes only the places that are wrong instead of rewriting the text, so the style and tone are kept. Each correction comes with the relevant article of the Korean orthography rules (for example Chapter 1 General Provisions, Article 2) plus an explanation and examples, which suits work that needs a reason for each edit. It also restores spacing in text with no spaces at all, such as speech recognition output or auto-generated captions, finds sentence boundaries and adds punctuation. Only Korean text is corrected.NoYesNot declaredNo
list_pos_tags바른 형태소 분석이 사용하는 47개 품사 태그 목록(코드·이름·대분류·소분류·enum)을 JSON 으로 돌려줍니다. analyze_syntax 결과의 품사 코드(NNG, JKS 등)를 해석할 때 참고하세요. EN: Returns the list of 47 part-of-speech tags used by Bareun morphological analysis (code, name, major class, subclass, enum) as JSON. Use it to interpret the POS codes (NNG, JKS and so on) in analyze_syntax results.NoYesNot declaredNo
search_dict우리말샘 사전을 자소(음소) 단위 슬롯 패턴으로 검색합니다. 완성형으로 표현할 수 없는 조건 — 초성·중성·종성 각각에 대한 조건('받침이 ㅎ인 용언', '중성이 ㅚ이고 받침 없는 1음절 어간') — 을 걸 수 있고, anchor=suffix 로 '-아지'·'-둥이'처럼 끝소리 검색도 됩니다. 각운(라임) 찾기, 초성 퀴즈·끝말잇기, 불규칙 활용 후보 수집처럼 글자를 자소로 쪼개야 풀리는 일에 씁니다. 색인 없이 사전 전체(약 100만 항목)를 훑으므로 넓은 패턴은 count_only 로 규모부터 확인하세요. EN: Searches the Urimalsaem dictionary (the open Korean dictionary) with jamo-level slot patterns. You can set conditions on the initial, medial and final of each syllable that cannot be written with whole syllables (for example a predicate whose final consonant is ㅎ, or a one-syllable stem with medial ㅚ and no final), and anchor=suffix also finds endings such as -아지 or -둥이. Use it for tasks that need letters split into jamo, such as finding rhymes, initial-consonant quizzes, word chains, and collecting irregular conjugation candidates. It scans the whole dictionary (about one million entries) without an index, so check the size of a broad pattern with count_only first.NoYesNot declaredNo
tokenize한국어 문장을 어절(토큰) 단위로 분리합니다. 품사 정보 없이 어절 경계만 필요할 때 쓰고, 형태소·품사가 필요하면 analyze_syntax 를 쓰세요. auto_spacing=true 를 주면 띄어쓰기가 어긋난 문장도 바로잡아 나눕니다. EN: Splits Korean text into words (tokens). Use it when you only need word boundaries without part-of-speech information, and use analyze_syntax when you need morphemes and POS tags. With auto_spacing=true it also fixes text whose spacing is wrong before splitting.NoYesNot declaredNo

Details

Registry status
Active
Published
Jun 9, 2026
Updated
Jun 9, 2026
Categories (suggested)
Data and analyticsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR
Not declared

Are you the operator? Claim this listing