WordNet MCP 服务
keepondream
README
WordNet MCP 服务
这是一个基于WordNet的Model Context Protocol (MCP) 服务实现,提供词汇查询功能,包括同义词、反义词、上位词和定义等。
项目地址
GitHub: github.com/keepondream/wordnet-mcp-server
功能
- 查询单词的同义词
- 查询单词的反义词
- 查询单词的上位词(更一般的概念)
- 查询单词的下位词(更具体的概念)
- 查询单词的定义和例句
- 获取单词的综合信息
安装
通过 PyPI 安装
推荐使用 uv 安装:
# 安装 wordnet-mcp-server
uvx wordnet-mcp-server
或者使用 pip:
# 安装 wordnet-mcp-server
pip install wordnet-mcp-server
从源码安装
# 克隆仓库
git clone https://github.com/keepondream/wordnet-mcp-server.git
cd wordnet-mcp-server
# 安装依赖和项目
uv pip install -e .
使用方法
直接运行
安装后,可以直接使用命令行运行服务:
# 使用入口点运行
wordnet-mcp
# 或者使用 Python 模块运行
python -m wordnet_mcp_server
在 MCP 客户端中配置服务
方法一:直接使用 uvx 命令(推荐)
当服务发布到 PyPI 后,您可以直接使用 uvx 命令配置(最简单的方式):
{
"mcpServers": {
"wordnet": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
方法二:指定 Python 解释器和模块路径
{
"mcpServers": {
"WordNet MCP": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
在 Cursor 中添加 MCP 服务
- 在 Cursor 中安装 MCP 服务
- 添加 WordNet MCP 服务(使用上述配置方式之一)
- 在使用时,可以选择所需的功能进行调用
示例
代码示例
# 查询单词 "happy" 的同义词
get_synonyms("happy")
# 查询单词 "happy" 的反义词
get_antonyms("happy")
# 获取单词 "happy" 的所有相关信息
get_word_info("happy")
在LLM对话中使用示例
配置好MCP服务后,您可以在与Claude、GPT等支持MCP的LLM对话时使用这些工具。以下是一些对话示例:
示例1:查询单词同义词
用户: 请帮我查找单词"improve"的同义词。
LLM: 我会使用WordNet工具查询"improve"的同义词。
[LLM调用get_synonyms工具]
"improve"的同义词包括:
- enhance
- ameliorate
- better
- meliorate
- advance
- improve upon
- improve on ...
示例2:获取单词的反义词
用户: "success"的反义词有哪些?
LLM: 让我查询"success"的反义词。
[LLM调用get_antonyms工具]
"success"的反义词包括:
- failure
- unsuccess
- ...
示例3:理解概念层次关系
用户: 我想了解"dog"在生物分类中的上位概念和下位概念。
LLM: 我会分别查询"dog"的上位词(更一般的概念)和下位词(更具体的概念)。
[LLM调用get_hypernyms和get_hyponyms工具]
"dog"的上位概念包括:
- canine
- domestic animal
- carnivore
- mammal ...
"dog"的下位概念包括:
- puppy
- pooch`
- hound
- poodle
- terrier
- retriever ...
示例4:查询综合信息
用户: 请给我详细介绍单词"time"的各种含义。
LLM: 我将查询"time"的综合信息。
[LLM调用get_word_info工具]
"time"的信息如下:
同义词:
- time period
- period of time
- period ...
定义:
- a nonspatial continuum in which events occur in apparently irreversible succession
- a quantity representing duration
- an instance or occasion ...
例句:
- "they were living in a time of great social change"
- "he was a great actor in his time" ...
开发
安装开发依赖
# 安装开发依赖
uv pip install -e ".[dev]"
使用 Makefile
项目提供了Makefile,可以轻松进行开发和发布操作:
# 递增版本号
make bump-version
# 构建包
make build
# 发布到PyPI
make publish
# 本地安装
make install
# 运行测试
make test
# 清理构建文件
make clean
# WordNet MCP 服务
这是一个基于WordNet的Model Context Protocol (MCP) 服务实现,提供词汇查询功能,包括同义词、反义词、上下位词和定义等。
## 项目地址
GitHub: [github.com/keepondream/wordnet-mcp-server](https://github.com/keepondream/wordnet-mcp-server)
## 功能
- 查询单词的同义词
- 查询单词的反义词
- 查询单词的上位词(更一般的概念)
- 查询单词的下位词(更具体的概念)
- 查询单词的定义和例句
- 获取单词的综合信息
## 安装
### 通过 PyPI 安装
推荐使用 [uv](https://github.com/astral-sh/uv) 安装:
```bash
# 安装 wordnet-mcp-server
uvx wordnet-mcp-server
或者使用 pip:
# 安装 wordnet-mcp-server
pip install wordnet-mcp-server
从源码安装
# 克隆仓库
git clone https://github.com/keepondream/wordnet-mcp-server.git
cd wordnet-mcp-server
# 安装依赖和项目
uv pip install -e .
使用方法
直接运行
安装后,可以直接使用命令行运行服务:
# 使用入口点运行
wordnet-mcp
# 或者使用 Python 模块运行
python -m wordnet_mcp_server
在 MCP 客户端中配置服务
方法一:直接使用 uvx 命令(推荐)
当服务发布到 PyPI 后,您可以直接使用 uvx 命令配置(最简单的方式):
{
"mcpServers": {
"wordnet": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
方法二:指定 Python 解释器和模块路径
{
"mcpServers": {
"WordNet MCP": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
在 Cursor 中添加 MCP 服务
- 在 Cursor 中安装 MCP 服务
- 添加 WordNet MCP 服务(使用上述配置方式之一)
- 在使用时,可以选择所需的功能进行调用
示例
代码示例
# 查询单词 "happy" 的同义词
get_synonyms("happy")
# 查询单词 "happy" 的反义词
get_antonyms("happy")
# 获取单词 "happy" 的所有相关信息
get_word_info("happy")
在LLM对话中使用示例
配置好MCP服务后,您可以在与Claude、GPT等支持MCP的LLM对话时使用这些工具。以下是一些对话示例:
示例1:查询单词同义词
用户: 请帮我查找单词"improve"的同义词。
LLM: 我会使用WordNet工具查询"improve"的同义词。
[LLM调用get_synonyms工具]
"improve"的同义词包括:
- enhance
- ameliorate
- better
- meliorate
- advance
- improve upon
- improve on ...
示例2:获取单词的反义词
用户: "success"的反义词有哪些?
LLM: 让我查询"success"的反义词。
[LLM调用get_antonyms工具]
"success"的反义词包括:
- failure
- unsuccess
- ...
示例3:理解概念层次关系
用户: 我想了解"dog"在生物分类中的上位概念和下位概念。
LLM: 我会分别查询"dog"的上位词(更一般的概念)和下位词(更具体的概念)。
[LLM调用get_hypernyms和get_hyponyms工具]
"dog"的上位概念包括:
- canine
- domestic animal
- carnivore
- mammal ...
"dog"的下位概念包括:
- puppy
- pooch`
- hound
- poodle
- terrier
- retriever ...
示例4:查询综合信息
用户: 请给我详细介绍单词"time"的各种含义。
LLM: 我将查询"time"的综合信息。
[LLM调用get_word_info工具]
"time"的信息如下:
同义词:
- time period
- period of time
- period ...
定义:
- a nonspatial continuum in which events occur in apparently irreversible succession
- a quantity representing duration
- an instance or occasion ...
例句:
- "they were living in a time of great social change"
- "he was a great actor in his time" ...
开发
安装开发依赖
# 安装开发依赖
uv pip install -e ".[dev]"
使用 Makefile
项目提供了Makefile,可以轻松进行开发和发布操作:
# 递增版本号
make bump-version
# 构建包
make build
# 发布到PyPI
make publish
# 本地安装
make install
# 运行测试
make test
# 清理构建文件
make clean
# WordNet MCP 服务
这是一个基于 WordNet 的 Model Context Protocol (MCP) 服务实现,提供词汇查询功能,包括同义词、反义词、上位词和定义等。
## 项目地址
GitHub: [github.com/keepondream/wordnet-mcp-server](https://github.com/keepondream/wordnet-mcp-server)
## 功能
- 查询单词的同义词
- 查询单词的反义词
- 查询单词的上位词(更一般的概念)
- 查询单词的下位词(更具体的概念)
- 查询单词的定义和例句
- 获取单词的综合信息
## 安装
### 通过 PyPI 安装
推荐使用 [uv](https://github.com/astral-sh/uv) 安装:
```bash
# 安装 wordnet-mcp-server
uvx wordnet-mcp-server
或者使用 pip:
# 安装 wordnet-mcp-server
pip install wordnet-mcp-server
从源码安装
# 克隆仓库
git clone https://github.com/keepondream/wordnet-mcp-server.git
cd wordnet-mcp-server
# 安装依赖和项目
uv pip install -e .
使用方法
直接运行
安装后,可以直接使用命令行运行服务:
# 使用入口点运行
wordnet-mcp
# 或者使用 Python 模块运行
python -m wordnet_mcp_server
在 MCP 客户端中配置服务
方法一:直接使用 uvx 命令(推荐)
当服务发布到 PyPI 后,您可以直接使用 uvx 命令配置(最简单的方式):
{
"mcpServers": {
"wordnet": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
方法二:指定 Python 解释器和模块路径
{
"mcpServers": {
"WordNet MCP": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
在 Cursor 中添加 MCP 服务
- 在 Cursor 中安装 MCP 服务
- 添加 WordNet MCP 服务(使用上述配置方式之一)
- 在使用时,可以选择所需的功能进行调用
示例
代码示例
# 查询单词 "happy" 的同义词
get_synonyms("happy")
# 查询单词 "happy" 的反义词
get_antonyms("happy")
# 获取单词 "happy" 的所有相关信息
get_word_info("happy")
在LLM对话中使用示例
配置好 MCP 服务后,您可以在与 Claude、GPT 等支持 MCP 的 LLM 对话时使用这些工具。以下是一些对话示例:
示例 1:查询单词同义词
用户: 请帮我查找单词 "improve" 的同义词。
LLM: 我会使用 WordNet 工具查询 "improve" 的同义词。
[LLM 调用 get_synonyms 工具]
"improve" 的同义词包括:
- enhance
- ameliorate
- better
- meliorate
- advance
- improve upon
- improve on ...
示例 2:获取单词的反义词
用户: "success" 的反义词有哪些?
LLM: 让我查询 "success" 的反义词。
[LLM 调用 get_antonyms 工具]
"success" 的反义词包括:
- failure
- unsuccess
- ...
示例 3:理解概念层次关系
用户: 我想了解 "dog" 在生物分类中的上位概念和下位概念。
LLM: 我会分别查询 "dog" 的上位词(更一般的概念)和下位词(更具体的概念)。
[LLM 调用 get_hypernyms 和 get_hyponyms 工具]
"dog" 的上位概念包括:
- canine
- domestic animal
- carnivore
- mammal ...
"dog" 的下位概念包括:
- puppy
- pooch`
- hound
- poodle
- terrier
- retriever ...
示例 4:查询综合信息
用户: 请给我详细介绍单词 "time" 的各种含义。
LLM: 我将查询 "time" 的综合信息。
[LLM 调用 get_word_info 工具]
"time" 的信息如下:
同义词:
- time period
- period of time
- period ...
定义:
- a nonspatial continuum in which events occur in apparently irreversible succession
- a quantity representing duration
- an instance or occasion ...
例句:
- "they were living in a time of great social change"
- "he was a great actor in his time" ...
开发
安装开发依赖
# 安装开发依赖
uv pip install -e ".[dev]"
使用 Makefile
项目提供了 Makefile,可以轻松进行开发和发布操作:
# 递增版本号
make bump-version
# 构建包
make build
# 发布到 PyPI
make publish
# 本地安装
make install
# 运行测试
make test
# 清理构建文件
make clean
# WordNet MCP 服务
这是一个基于 WordNet 的 Model Context Protocol (MCP) 服务实现,提供词汇查询功能,包括同义词、反义词、上位词和定义等。
## 项目地址
GitHub: [github.com/keepondream/wordnet-mcp-server](https://github.com/keepondream/wordnet-mcp-server)
## 功能
- 查询单词的同义词
- 查询单词的反义词
- 查询单词的上位词(更一般的概念)
- 查询单词的下位词(更具体的概念)
- 查询单词的定义和例句
- 获取单词的综合信息
## 安装
### 通过 PyPI 安装
推荐使用 [uv](https://github.com/astral-sh/uv) 安装:
```bash
# 安装 wordnet-mcp-server
uvx wordnet-mcp-server
或者使用 pip:
# 安装 wordnet-mcp-server
pip install wordnet-mcp-server
从源码安装
# 克隆仓库
git clone https://github.com/keepondream/wordnet-mcp-server.git
cd wordnet-mcp-server
# 安装依赖和项目
uv pip install -e .
使用方法
直接运行
安装后,可以直接使用命令行运行服务:
# 使用入口点运行
wordnet-mcp
# 或者使用 Python 模块运行
python -m wordnet_mcp_server
在 MCP 客户端中配置服务
方法一:直接使用 uvx 命令(推荐)
当服务发布到 PyPI 后,您可以直接使用 uvx 命令配置(最简单的方式):
{
"mcpServers": {
"wordnet": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
方法二:指定 Python 解释器和模块路径
{
"mcpServers": {
"WordNet MCP": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
在 Cursor 中添加 MCP 服务
- 在 Cursor 中安装 MCP 服务
- 添加 WordNet MCP 服务(使用上述配置方式之一)
- 在使用时,可以选择所需的功能进行调用
示例
代码示例
# 查询单词 "happy" 的同义词
get_synonyms("happy")
# 查询单词 "happy" 的反义词
get_antonyms("happy")
# 获取单词 "happy" 的所有相关信息
get_word_info("happy")
在LLM对话中使用示例
配置好 MCP 服务后,您可以在与 Claude、GPT 等支持 MCP 的 LLM 对话时使用这些工具。以下是一些对话示例:
示例 1:查询单词同义词
用户: 请帮我查找单词 "improve" 的同义词。
LLM: 我会使用 WordNet 工具查询 "improve" 的同义词。
[LLM 调用 get_synonyms 工具]
"improve" 的同义词包括:
- enhance
- ameliorate
- better
- meliorate
- advance
- improve upon
- improve on ...
示例 2:获取单词的反义词
用户: "success" 的反义词有哪些?
LLM: 让我查询 "success" 的反义词。
[LLM 调用 get_antonyms 工具]
"success" 的反义词包括:
- failure
- unsuccess
- ...
示例 3:理解概念层次关系
用户: 我想了解 "dog" 在生物分类中的上位概念和下位概念。
LLM: 我会分别查询 "dog" 的上位词(更一般的概念)和下位词(更具体的概念)。
[LLM 调用 get_hypernyms 和 get_hyponyms 工具]
"dog" 的上位概念包括:
- canine
- domestic animal
- carnivore
- mammal ...
"dog" 的下位概念包括:
- puppy
- pooch
- hound
- poodle
- terrier
- retriever ...
示例 4:查询综合信息
用户: 请给我详细介绍单词 "time" 的各种含义。
LLM: 我将查询 "time" 的综合信息。
[LLM 调用 get_word_info 工具]
"time" 的信息如下:
同义词:
- time period
- period of time
- period ...
定义:
- a nonspatial continuum in which events occur in apparently irreversible succession
- a quantity representing duration
- an instance or occasion ...
例句:
- "they were living in a time of great social change"
- "he was a great actor in his time" ...
开发
安装开发依赖
# 安装开发依赖
uv pip install -e ".[dev]"
使用 Makefile
项目提供了 Makefile,可以轻松进行开发和发布操作:
# 递增版本号
make bump-version
# 构建包
make build
# 发布到 PyPI
make publish
# 本地安装
make install
# 运行测试
make test
# 清理构建文件
make clean
# WordNet MCP 服务
这是一个基于 WordNet 的 Model Context Protocol (MCP) 服务实现,提供词汇查询功能,包括同义词、反义词、上位词和定义等。
## 项目地址
GitHub: [github.com/keepondream/wordnet-mcp-server](https://github.com/keepondream/wordnet-mcp-server)
## 功能
- 查询单词的同义词
- 查询单词的反义词
- 查询单词的上位词(更一般的概念)
- 查询单词的下位词(更具体的概念)
- 查询单词的定义和例句
- 获取单词的综合信息
## 安装
### 通过 PyPI 安装
推荐使用 [uv](https://github.com/astral-sh/uv) 安装:
```bash
# 安装 wordnet-mcp-server
uvx wordnet-mcp-server
或者使用 pip:
# 安装 wordnet-mcp-server
pip install wordnet-mcp-server
从源码安装
# 克隆仓库
git clone https://github.com/keepondream/wordnet-mcp-server.git
cd wordnet-mcp-server
# 安装依赖和项目
uv pip install -e .
使用方法
直接运行
安装后,可以直接使用命令行运行服务:
# 使用入口点运行
wordnet-mcp
# 或者使用 Python 模块运行
python -m wordnet_mcp_server
在 MCP 客户端中配置服务
方法一:直接使用 uvx 命令(推荐)
当服务发布到 PyPI 后,您可以直接使用 uvx 命令配置(最简单的方式):
{
"mcpServers": {
"wordnet": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
方法二:指定 Python 解释器和模块路径
{
"mcpServers": {
"WordNet MCP": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
在 Cursor 中添加 MCP 服务
- 在 Cursor 中安装 MCP 服务
- 添加 WordNet MCP 服务(使用上述配置方式之一)
- 在使用时,可以选择所需的功能进行调用
示例
代码示例
# 查询单词 "happy" 的同义词
get_synonyms("happy")
# 查询单词 "happy" 的反义词
get_antonyms("happy")
# 获取单词 "happy" 的所有相关信息
get_word_info("happy")
在LLM对话中使用示例
配置好 MCP 服务后,您可以在与 Claude、GPT 等支持 MCP 的 LLM 对话时使用这些工具。以下是一些对话示例:
示例 1:查询单词同义词
用户: 请帮我查找单词 "improve" 的同义词。
LLM: 我会使用 WordNet 工具查询 "improve" 的同义词。
[LLM 调用 get_synonyms 工具]
"improve" 的同义词包括:
- enhance
- ameliorate
- better
- meliorate
- advance
- improve upon
- improve on ...
示例 2:获取单词的反义词
用户: "success" 的反义词有哪些?
LLM: 让我查询 "success" 的反义词。
[LLM 调用 get_antonyms 工具]
"success" 的反义词包括:
- failure
- unsuccess
- ...
示例 3:理解概念层次关系
用户: 我想了解 "dog" 在生物分类中的上位概念和下位概念。
LLM: 我会分别查询 "dog" 的上位词(更一般的概念)和下位词(更具体的概念)。
[LLM 调用 get_hypernyms 和 get_hyponyms 工具]
"dog" 的上位概念包括:
- canine
- domestic animal
- carnivore
- mammal ...
"dog" 的下位概念包括:
- puppy
- pooch
- hound
- poodle
- terrier
- retriever ...
示例 4:查询综合信息
用户: 请给我详细介绍单词 "time" 的各种含义。
LLM: 我将查询 "time" 的综合信息。
[LLM 调用 get_word_info 工具]
"time" 的信息如下:
同义词:
- time period
- period of time
- period ...
定义:
- a nonspatial continuum in which events occur in apparently irreversible succession
- a quantity representing duration
- an instance or occasion ...
例句:
- "they were living in a time of great social change"
- "he was a great actor in his time" ...
开发
安装开发依赖
# 安装开发依赖
uv pip install -e ".[dev]"
使用 Makefile
项目提供了 Makefile,可以轻松进行开发和发布操作:
# 递增版本号
make bump-version
# 构建包
make build
# 发布到 PyPI
make publish
# 本地安装
make install
# 运行测试
make test
# 清理构建文件
make clean
# WordNet MCP 服务
这是一个基于 WordNet 的 Model Context Protocol (MCP) 服务实现,提供词汇查询功能,包括同义词、反义词、上位词和定义等。
## 项目地址
GitHub: [github.com/keepondream/wordnet-mcp-server](https://github.com/keepondream/wordnet-mcp-server)
## 功能
- 查询单词的同义词
- 查询单词的反义词
- 查询单词的上位词(更一般的概念)
- 查询单词的下位词(更具体的概念)
- 查询单词的定义和例句
- 获取单词的综合信息
## 安装
### 通过 PyPI 安装
推荐使用 [uv](https://github.com/astral-sh/uv) 安装:
```bash
# 安装 wordnet-mcp-server
uvx wordnet-mcp-server
或者使用 pip:
# 安装 wordnet-mcp-server
pip install wordnet-mcp-server
从源码安装
# 克隆仓库
git clone https://github.com/keepondream/wordnet-mcp-server.git
cd wordnet-mcp-server
# 安装依赖和项目
uv pip install -e .
使用方法
直接运行
安装后,可以直接使用命令行运行服务:
# 使用入口点运行
wordnet-mcp
# 或者使用 Python 模块运行
python -m wordnet_mcp_server
在 MCP 客户端中配置服务
方法一:直接使用 uvx 命令(推荐)
当服务发布到 PyPI 后,您可以直接使用 uvx 命令配置(最简单的方式):
{
"mcpServers": {
"wordnet": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
方法二:指定 Python 解释器和模块路径
{
"mcpServers": {
"WordNet MCP": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
在 Cursor 中添加 MCP 服务
- 在 Cursor 中安装 MCP 服务
- 添加 WordNet MCP 服务(使用上述配置方式之一)
- 在使用时,可以选择所需的功能进行调用
示例
代码示例
# 查询单词 "happy" 的同义词
get_synonyms("happy")
# 查询单词 "happy" 的反义词
get_antonyms("happy")
# 获取单词 "happy" 的所有相关信息
get_word_info("happy")
在LLM对话中使用示例
配置好 MCP 服务后,您可以在与 Claude、GPT 等支持 MCP 的 LLM 对话时使用这些工具。以下是一些对话示例:
示例 1:查询单词同义词
用户: 请帮我查找单词 "improve" 的同义词。
LLM: 我会使用 WordNet 工具查询 "improve" 的同义词。
[LLM 调用 get_synonyms 工具]
"improve" 的同义词包括:
- enhance
- ameliorate
- better
- meliorate
- advance
- improve upon
- improve on ...
示例 2:获取单词的反义词
用户: "success" 的反义词有哪些?
LLM: 让我查询 "success" 的反义词。
[LLM 调用 get_antonyms 工具]
"success" 的反义词包括:
- failure
- unsuccess
- ...
示例 3:理解概念层次关系
用户: 我想了解 "dog" 在生物分类中的上位概念和下位概念。
LLM: 我会分别查询 "dog" 的上位词(更一般的概念)和下位词(更具体的概念)。
[LLM 调用 get_hypernyms 和 get_hyponyms 工具]
"dog" 的上位概念包括:
- canine
- domestic animal
- carnivore
- mammal ...
"dog" 的下位概念包括:
- puppy
- pooch
- hound
- poodle
- terrier
- retriever ...
示例 4:查询综合信息
用户: 请给我详细介绍单词 "time" 的各种含义。
LLM: 我将查询 "time" 的综合信息。
[LLM 调用 get_word_info 工具]
"time" 的信息如下:
同义词:
- time period
- period of time
- period ...
定义:
- a nonspatial continuum in which events occur in apparently irreversible succession
- a quantity representing duration
- an instance or occasion ...
例句:
- "they were living in a time of great social change"
- "he was a great actor in his time" ...
开发
安装开发依赖
# 安装开发依赖
uv pip install -e ".[dev]"
使用 Makefile
项目提供了 Makefile,可以轻松进行开发和发布操作:
# 递增版本号
make bump-version
# 构建包
make build
# 发布到 PyPI
make publish
# 本地安装
make install
# 运行测试
make test
# 清理构建文件
make clean
# WordNet MCP 服务
这是一个基于 WordNet 的 Model Context Protocol (MCP) 服务实现,提供词汇查询功能,包括同义词、反义词、上位词和定义等。
## 项目地址
GitHub: [github.com/keepondream/wordnet-mcp-server](https://github.com/keepondream/wordnet-mcp-server)
## 功能
- 查询单词的同义词
- 查询单词的反义词
- 查询单词的上位词(更一般的概念)
- 查询单词的下位词(更具体的概念)
- 查询单词的定义和例句
- 获取单词的综合信息
## 安装
### 通过 PyPI 安装
推荐使用 [uv](https://github.com/astral-sh/uv) 安装:
```bash
# 安装 wordnet-mcp-server
uvx wordnet-mcp-server
或者使用 pip:
# 安装 wordnet-mcp-server
pip install wordnet-mcp-server
从源码安装
# 克隆仓库
git clone https://github.com/keepondream/wordnet-mcp-server.git
cd wordnet-mcp-server
# 安装依赖和项目
uv pip install -e .
使用方法
直接运行
安装后,可以直接使用命令行运行服务:
# 使用入口点运行
wordnet-mcp
# 或者使用 Python 模块运行
python -m wordnet_mcp_server
在 MCP 客户端中配置服务
方法一:直接使用 uvx 命令(推荐)
当服务发布到 PyPI 后,您可以直接使用 uvx 命令配置(最简单的方式):
{
"mcpServers": {
"wordnet": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
方法二:指定 Python 解释器和模块路径
{
"mcpServers": {
"WordNet MCP": {
"command": "python3",
"type": "stdio",
"args": ["-m", "wordnet_mcp_server"]
}
}
}
在 Cursor 中添加 MCP 服务
- 在 Cursor 中安装 MCP 服务
- 添加 WordNet MCP 服务(使用上述配置方式之一)
- 在使用时,可以选择所需的功能进行调用
示例
代码示例
# 查询单词 "happy" 的同义词
get_synonyms("happy")
# 查询单词 "happy" 的反义词
get_antonyms("happy")
# 获取单词 "happy" 的所有相关信息
get_word_info("happy")
在LLM对话中使用示例
配置好 MCP 服务后,您可以在与 Claude、GPT 等支持 MCP 的 LLM 对话时使用这些工具。以下是一些对话示例:
示例 1:查询单词同义词
用户: 请帮我查找单词 "improve" 的同义词。
LLM: 我会使用 WordNet 工具查询 "improve" 的同义词。
[LLM 调用 get_synonyms 工具]
"improve" 的同义词包括:
- enhance
- ameliorate
- better
- meliorate
推荐服务器
Crypto Price & Market Analysis MCP Server
一个模型上下文协议 (MCP) 服务器,它使用 CoinCap API 提供全面的加密货币分析。该服务器通过一个易于使用的界面提供实时价格数据、市场分析和历史趋势。 (Alternative, slightly more formal and technical translation): 一个模型上下文协议 (MCP) 服务器,利用 CoinCap API 提供全面的加密货币分析服务。该服务器通过用户友好的界面,提供实时价格数据、市场分析以及历史趋势数据。
MCP PubMed Search
用于搜索 PubMed 的服务器(PubMed 是一个免费的在线数据库,用户可以在其中搜索生物医学和生命科学文献)。 我是在 MCP 发布当天创建的,但当时正在度假。 我看到有人在您的数据库中发布了类似的服务器,但还是决定发布我的服务器。
mixpanel
连接到您的 Mixpanel 数据。 从 Mixpanel 分析查询事件、留存和漏斗数据。

Sequential Thinking MCP Server
这个服务器通过将复杂问题分解为顺序步骤来促进结构化的问题解决,支持修订,并通过完整的 MCP 集成来实现多条解决方案路径。

Nefino MCP Server
为大型语言模型提供访问德国可再生能源项目新闻和信息的能力,允许按地点、主题(太阳能、风能、氢能)和日期范围进行筛选。
Vectorize
将 MCP 服务器向量化以实现高级检索、私有深度研究、Anything-to-Markdown 文件提取和文本分块。
Mathematica Documentation MCP server
一个服务器,通过 FastMCP 提供对 Mathematica 文档的访问,使用户能够从 Wolfram Mathematica 检索函数文档和列出软件包符号。
kb-mcp-server
一个 MCP 服务器,旨在实现便携性、本地化、简易性和便利性,以支持对 txtai “all in one” 嵌入数据库进行基于语义/图的检索。任何 tar.gz 格式的 txtai 嵌入数据库都可以被加载。
Research MCP Server
这个服务器用作 MCP 服务器,与 Notion 交互以检索和创建调查数据,并与 Claude Desktop Client 集成以进行和审查调查。

Cryo MCP Server
一个API服务器,实现了模型补全协议(MCP),用于Cryo区块链数据提取,允许用户通过任何兼容MCP的客户端查询以太坊区块链数据。