MCP Jieba Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Jieba Server
这是一个基于 rjieba (Rust implementation of Jieba) 的 Model Context Protocol (MCP) 服务器,提供高性能的中文分词服务。
功能特性
高性能分词: 使用 Rust 编写的底层引擎。
多模式支持: 支持精确模式 (
exact) 和搜索引擎模式 (search)。词性标注: 支持 ICTCLAS 兼容的词性标注。
关键词提取: 基于 BM25 算法的关键词提取。
批量处理: 支持单字符串或字符串数组输入,返回 JSON 格式结果。
双模部署:
STDIO: 适用于本地开发和 Claude Context/Cherry Studio/VS Code 集成。
Streamable-HTTP: 适用于远程部署(如 ModelScope)。
Related MCP server: MyMcp
安装
使用 pip / uv / pipx
# 使用 pip
pip install .
# 使用 uv
uv pip install .使用方法
1. 本地运行 (STDIO)
直接运行模块即可启动 STDIO 服务器:
python -m mcp_jieba.server或者在 Claude Context/Cherry Studio/VS Code 的 MCP 配置中添加:
{
"mcpServers": {
"jieba": {
"command": "python",
"args": ["-m", "mcp_jieba.server"]
}
}
}2. 远程部署 (Streamable-HTTP)
使用命令行参数启动 HTTP 服务器:
python -m mcp_jieba.server --transport http --host 0.0.0.0 --port 8000SSE 端点地址: http://localhost:8000/sse
ModelScope 部署
在 ModelScope 创建 Space 时,选择 Python 环境,并使用以下启动命令:
python -m mcp_jieba.server --transport http --host 0.0.0.0 --port 8000当前 pyproject.toml 已经包含所有依赖。
开发与测试
目前项目的单元测试尚不完善。建议使用 MCP Inspector 进行交互式测试和调试。
bunx @modelcontextprotocol/inspector python -m mcp_jieba.server工具说明
tokenize
对文本进行分词。
项目 | 描述 |
参数 |
|
返回 | JSON 对象,键为输入数组的索引(字符串格式),值为分词结果数组。 |
示例:
输入:
text=["我爱北京天安门"], mode="exact"输出:
{"0": ["我", "爱", "北京", "天安门"]}
tag
对文本进行词性标注,标注类型符合ICTCLAS标准。
项目 | 描述 |
参数 |
|
返回 | JSON 对象,键为输入数组的索引,值为单词-词性对的列表。 |
示例:
输入:
text=["我爱北京天安门"]输出:
{"0": [{"word": "我", "flag": "r"}, {"word": "爱", "flag": "v"}, ...]}
extract_keywords
使用向量化的针对关键词BM25-ADPT算法提取关键词。
项目 | 描述 |
参数 |
|
返回 | JSON 对象,键为输入数组的索引,值为关键词列表。 |
示例:
输入:
text=["我爱北京天安门"], top_k=2输出:
{"0": ["天安门", "北京"]}
鸣谢
@messense/jieba-rs
@messense/rjieba-py
BM25-ADPT https://doi.org/10.1145/2063576.2063871
GitHub Copilot
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Chinese dictionary (124k entries), HSK levels, text segmentation and 195 grammar points.
MCP server for Chinese dictionary lookup: character definitions, pinyin, stroke order and word
Authoritative JLPT-graded Japanese dataset (kanji, vocab, grammar, history) via MCP and REST.
Search 386+ AI tools with China-access data, live GitHub stats, 4-language metadata. No key needed
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables Chinese text segmentation using the jieba library with support for precise, full, and search engine modes. Provides natural language access to professional Chinese word segmentation capabilities through MCP protocol.52MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that counts the number of Chinese characters (excluding punctuation, spaces, English, and numbers) in a given text, compatible with Streamable HTTP and JSON-RPC.MIT
- AlicenseAqualityBmaintenanceEnables natural language search and retrieval of Korean laws, precedents, administrative rules, and legal terms, with deep legal chain analysis and full-text access. Supports stdio and streamable-http transports for local and remote deployment.10MIT
- AlicenseAqualityCmaintenanceProvides on-device Chinese speech recognition with traditional Chinese (Taiwan) output via MCP server, HTTP API, and CLI, ensuring privacy by processing audio locally without uploading to cloud services.21MIT