Korean NLP MCP server: morphological analysis, tokenization, spell & grammar checking (Bareun)
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Grammar Checking.
analyze_syntaxSplits a sentence into words/morphemes and tags parts of speech (morphological analysis).
analyze_syntax_rawSame analysis **without post-processing** (no compound-noun/verb splitting, no auto spacing, no custom dictionaries) β the raw model output.
search_dictSearches the Urimalsaem Korean dictionary (~1.1M entries) by **jamo (phoneme-level) slot patterns** β conditions like "verbs whose stem ends in the γ coda" or "words ending in -μμ§" that cannot be expressed with composed Hangul syllables.
tokenizeSplits a sentence into word (token) units.
correct_grammarCorrects spelling/spacing and returns correction blocks.
list_pos_tagsReturns the 47 part-of-speech tags Bareun uses (code Β· name Β· class).
λ°λ₯Έ(Bareun) is a Korean natural-language platform. This is its MCP (Model Context Protocol) server β it lets any MCP-compatible AI tool (Claude, Cursor, VS Code, Claude Desktop, β¦) perform Korean morphological analysis and spell/grammar correction by calling Bareun as a tool.
Large language models still miss the subtle spacing, particle agreement, and confusable-word rules of Korean. Plug Bareun in as an MCP tool and your agent can hand off analysis and proofreading to a dedicated Korean engine, then use the result to produce more accurate Korean output.
https://api.bareun.ai/mcpapi-key header or Authorization: Bearer <key>)The
/mcpendpoint is available on the spell-checkerβincluded build of Bareun (the morphological-analysis-only build does not expose/mcp). The same endpoint works on self-hosted/on-prem installs β just swap the host.
Spelling & spacing β correct_grammar (real output from https://api.bareun.ai/mcp):
| In | νμκ²°κ³Όλ₯Ό μ 리ν΄μ λ΄μΌκΉμ§ 보λ΄μ£ΌμκΈ° λ°λλλ€. |
| Out | νμ κ²°κ³Όλ₯Ό μ 리ν΄μ λ΄μΌκΉμ§ λ³΄λ΄ μ£ΌμκΈ° λ°λλλ€. |
Every fix comes back as a block, so an agent can explain the edit instead of silently rewriting the sentence:
| Original | Corrected | Category | Rule |
|---|---|---|---|
| νμκ²°κ³Όλ₯Ό | νμ κ²°κ³Όλ₯Ό | SPACING | compound noun spacing |
| 보λ΄μ£ΌμκΈ° | λ³΄λ΄ μ£ΌμκΈ° | SPACING | auxiliary-verb spacing |
| λ°λλλ€. | λ°λλλ€. | TYPO | misspelling |
Morphological analysis β analyze_syntax (format: compact):
| In | λλ νκ΅μ κ°λ€. |
| Out | λ/NP λ/JX νκ΅/NNG μ/JKB κ°/VV γ΄λ€/EF ./SF |
Homograph senses β analyze_syntax with with_sense: true (beta): λ°° in λ°°κ° μνλ€
comes back with senseNo: 1 and its dictionary definition β μ¬λμ΄λ λλ¬Όμ λͺΈμμ β¦
κ°μ΄κ³Ό μλ©μ΄ μ¬μ΄μ λΆμ (belly, probability 0.87), plus the Urimalsaem entry id β so the
agent knows which λ°° it is reading.
| Tool | What it does | Key inputs |
|---|---|---|
analyze_syntax | Splits a sentence into words/morphemes and tags parts of speech (morphological analysis). | text (required), auto_split_sentence, auto_spacing, auto_jointing, custom_dict_names, encoding, format (full|compact), with_sense |
analyze_syntax_raw | Same analysis without post-processing (no compound-noun/verb splitting, no auto spacing, no custom dictionaries) β the raw model output. | text (required), auto_split_sentence, encoding, format, with_sense |
search_dict | Searches the Urimalsaem Korean dictionary (~1.1M entries) by jamo (phoneme-level) slot patterns β conditions like "verbs whose stem ends in the γ coda" or "words ending in -μμ§" that cannot be expressed with composed Hangul syllables. | pattern (required), anchor (word|prefix|suffix|contains), pos, std_only, with_definition, limit, count_only |
tokenize | Splits a sentence into word (token) units. | text (required), auto_spacing, encoding |
correct_grammar | Corrects spelling/spacing and returns correction blocks. | text (required), custom_dict_names, + 9 boolean correction options |
list_pos_tags | Returns the 47 part-of-speech tags Bareun uses (code Β· name Β· class). | (none) |
correct_grammar options (all boolean, default off): treat_as_title,
disable_split_sentence, disable_caret_spacing, disable_vx_spacing,
enable_limited_punctuation, disable_confusion, enable_cleanup_whitespace,
disable_typo_correction, enable_sentence_check.
encoding controls the unit for morpheme offsets: utf32 (default, code points
β matches Python), utf16 (JS/Java), utf8 (bytes β Go/C++).
with_sense β homograph sense disambiguation (WSD, beta). Korean writes many
unrelated words identically: λ°° can be belly, ship, or pear. Set with_sense: true
on analyze_syntax/analyze_syntax_raw and each content morpheme carries a sense
object β the dictionary sense number, its Korean definition, the Urimalsaem entry id, and
the probability of the chosen sense among that word's candidate senses. It is off by
default (one extra model pass; responses are byte-identical to before when omitted),
and format=compact renders it inline as λ°°__002/NNG. This feature is in beta and
ships officially with Bareun 3.1.0.
| Resource URI | Contents | Auth |
|---|---|---|
bareun://pos-tags | The 47 POS tags (code Β· name Β· class) β same data as list_pos_tags | API key |
bareun://server-info | Server metadata β name Β· version Β· build Β· active tools/resources | API key |
bareun://custom-dicts | Names of custom-dictionary domains registered for the key | valid API key |
Tip β register globally. Most tools default to project scope (the server is only available in one project). To use Bareun across all your projects, register it at global / user scope as shown below.
Omit -s user for project-local scope. Check with claude mcp get bareun.
Global: ~/.cursor/mcp.json Β· Project: <project>/.cursor/mcp.json
Global: run MCP: Open User Configuration Β· Project: <project>/.vscode/mcp.json
claude_desktop_config.jsonClaude Desktop bridges header-authenticated remote servers via mcp-remote
(Node.js required):
cline_mcp_settings.jsonOpen MCP Servers β Configure MCP Servers in Cline, then add:
All five tools are read-only (readOnlyHint), so listing them in autoApprove is
safe if you would rather not confirm every call.
ChatGPT talks to Streamable HTTP servers directly β no directory review needed. Turn on Developer mode (Settings β Apps & Connectors β Advanced), then Create a connector:
https://api.bareun.ai/mcpapi-key header works just as well.)Menu wording and plan availability shift between ChatGPT releases β Developer mode is an account-level toggle, and on Business/Enterprise a workspace owner enables it first.
Set Transport to Streamable HTTP, URL to https://api.bareun.ai/mcp, and
add header api-key: YOUR_API_KEY.
The contents of this repository (documentation, registry manifests, examples) are released under the MIT License. The Bareun engine itself is a proprietary service operated by Baikal AI; access is governed by the bareun.ai terms of service.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/bareun-korean-nlp-spell-grammar-checking)<a href="https://allmcps.com/mcp/bareun-korean-nlp-spell-grammar-checking"><img src="https://allmcps.com/api/badge/bareun-korean-nlp-spell-grammar-checking?style=directory" alt="Grammar Checking on AllMCPs" /></a>