Skip to main content
Glama

blackmount-nlp-mcp

PyPI version License: MIT Python 3.10+

面向 MCP 的 NLP 工具 — 零繁重依赖。Blackmount 构建。

作为 FastMCP 服务器提供 45 种文本分析工具。无需 NLTK,无需 spaCy,无需 transformers。仅有一个依赖项 (mcp[cli]),NLP 代码量不到 50 KB,秒级就绪。需要 Python 3.10+。


为什么选择它

blackmount-nlp-mcp

NLTK

spaCy

transformers

Wheel 大小

42 KB

1.5 MB

6 MB+ (+ 模型)

10 MB+ (+ 模型)

直接依赖

1

分词

情感分析

可读性评分

关键词提取

文本相似度

语言检测

✅ (18 种语言)

所有功能均使用纯 Python 从零实现 — 包括 Porter 词干提取、TF-IDF、RAKE、Levenshtein 距离、VADER 风格情感分析、Flesch / Gunning Fog / Coleman-Liau / ARI / SMOG 可读性评分、抽取式摘要、语言检测 — 此外还内置了 2000+ 词的情感词典和 500+ 停用词列表,全部打包在内。


Related MCP server: LODA MCP Server

快速开始

pip install blackmount-nlp-mcp

Claude Desktop

添加到你的配置文件中:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "nlp": {
      "command": "blackmount-nlp-mcp"
    }
  }
}

Cursor

添加到项目根目录的 .cursor/mcp.json 中:

{
  "mcpServers": {
    "nlp": {
      "command": "blackmount-nlp-mcp"
    }
  }
}

任意 MCP 客户端

服务器通过 stdio 运行。将你的客户端指向 blackmount-nlp-mcp 命令:

blackmount-nlp-mcp

重启编辑器。现在所有 45 种 NLP 工具均已可用 — 只需用自然语言提问即可。


工具目录

分词 (4 种工具)

工具

描述

尝试提问

word_tokenize

将文本拆分为单词,处理缩写和标点符号

"Tokenize this paragraph into words"

sentence_tokenize

拆分为句子,处理常见缩写

"Break this text into individual sentences"

generate_ngrams

从词元列表中生成词级 n-grams

"Generate bigrams from these tokens"

generate_char_ngrams

生成字符级 n-grams

"Get character trigrams for this word"

可读性 (8 种工具)

所有可读性函数在输入为空或仅包含空格时返回 0.0

工具

描述

尝试提问

flesch_reading_ease

0–100 易读性得分(越高越容易)

"Calculate the Flesch Reading Ease score"

flesch_kincaid_grade

美国年级水平估算

"What grade level is this written at?"

gunning_fog_index

基于复杂词比例的 Fog 指数

"Calculate the Fog index for this text"

coleman_liau_index

Coleman-Liau 年级水平指数

"Get the Coleman-Liau score"

automated_readability_index

ARI 年级水平指数

"What's the ARI for this document?"

smog_grade_index

SMOG 年级(推荐用于医疗文本)

"Calculate the SMOG grade for this document"

count_syllables

任意单词的音节计数估算

"How many syllables in 'extraordinary'?"

get_reading_level

一次调用获取所有可读性评分及纯英文标签

"Give me a full readability report for this text"

情感分析 (4 种工具)

工具

描述

尝试提问

get_sentiment_score

-1.0 到 +1.0 的复合情感得分

"What's the sentiment of this customer review?"

get_sentiment_label

返回 positive(正面)、negative(负面)或 neutral(中性)

"Is this feedback positive or negative?"

get_sentence_sentiments

逐句情感分析

"Show me the sentiment of each sentence"

get_aspect_sentiment

针对特定主题的情感分析

"What's the sentiment around 'pricing' in these reviews?"

关键词提取 (4 种工具)

工具

描述

尝试提问

extract_tfidf_keywords

语料库中的 TF-IDF 关键词排名

"What are the key terms across these docs?"

extract_rake_keywords

RAKE 算法 — 短语级关键词提取

"Extract the key phrases from this article"

get_word_frequency

按频率排序的最高频词(排除停用词)

"What are the most common words in this text?"

get_phrase_frequency

按频率排序的最高频 n-gram 短语

"What two-word phrases appear most often?"

文本相似度 (5 种工具)

工具

描述

尝试提问

get_jaccard_similarity

词集重叠度,0–1

"How similar are these two paragraphs?"

get_cosine_similarity

词袋余弦相似度,0–1

"Calculate cosine similarity between these texts"

get_edit_distance

Levenshtein 编辑距离

"How many edits to turn 'kitten' into 'sitting'?"

get_normalized_edit_distance

归一化到 0–1 的编辑距离

"How different are these two strings?"

get_longest_common_subsequence

两个字符串之间的 LCS 长度

"What's the LCS length of these two strings?"

文本清洗 (10 种工具)

工具

描述

尝试提问

clean_remove_stopwords

去除 500+ 个英语停用词

"Remove stopwords from this text"

clean_remove_punctuation

去除所有标点符号

"Strip the punctuation"

clean_remove_numbers

去除数字词元

"Remove all numbers from this"

clean_remove_urls

去除 URL

"Clean out the URLs"

clean_remove_emails

去除电子邮件地址

"Remove email addresses from this text"

clean_remove_html

去除 HTML 标签

"Strip the HTML from this content"

clean_normalize_whitespace

合并并修剪空白字符

"Normalize the whitespace"

clean_lowercase

将文本转换为小写

"Convert this to lowercase"

porter_stem

Porter 词干提取器(纯 Python,无 NLTK)

"Stem the word 'running'"

clean_text_pipeline

可配置的多步清洗流水线

"Clean this text: remove HTML, URLs, and stopwords"

检测 (8 种工具)

工具

描述

尝试提问

detect_text_language

识别 18 种支持的语言

"What language is this text written in?"

detect_text_encoding_type

检测脚本类型:ASCII, Latin, Cyrillic, CJK, Arabic

"What script does this text use?"

check_is_english

英语置信度得分,0–1

"Is this text in English?"

count_words

单词计数

"How many words are in this?"

count_sentences

句子计数

"Count the sentences"

count_paragraphs

段落计数

"How many paragraphs?"

get_avg_word_length

平均单词长度(字符数)

"What's the average word length?"

get_avg_sentence_length

平均句子长度(单词数)

"How long are the sentences on average?"

摘要 (2 种工具)

工具

描述

尝试提问

get_extractive_summary

从文档中选择 N 个得分最高的句子

"Summarize this article in 3 sentences"

get_text_statistics

完整的文档统计:单词数、可读性、语言、阅读时间

"Give me a statistical profile of this text"


作为库使用

子模块可直接导入 — 无需 MCP 服务器:

from blackmount_nlp_mcp.sentiment import sentiment_score, sentiment_label
from blackmount_nlp_mcp.readability import reading_level
from blackmount_nlp_mcp.keywords import rake_keywords

text = "This product is absolutely amazing! The quality is excellent."

print(sentiment_score(text))
# 0.9285

print(sentiment_label(text))
# 'positive'

print(reading_level(text))
# {'grade_level': 12.39, 'label': 'college',
#  'flesch_reading_ease': 14.27, 'flesch_kincaid_grade': 12.39,
#  'gunning_fog': 19.58, 'coleman_liau': 10.94,
#  'automated_readability': 7.51, 'smog_grade': 11.21}

print(rake_keywords(text))
# [{'phrase': 'absolutely amazing', 'score': 4.0},
#  {'phrase': 'product', 'score': 1.0},
#  {'phrase': 'quality', 'score': 1.0},
#  {'phrase': 'excellent', 'score': 1.0}]

开发

git clone https://github.com/BlackMount-ai/blackmount-nlp-mcp
cd blackmount-nlp-mcp
pip install -e .
pytest tests/ -v

Blackmount 生态系统

blackmount-nlp-mcp 由 Blackmount 构建 — 为 AI 从业者打造的工具。

blackmount-mcp — 作为 MCP 服务器提供浏览器记忆、AI 聊天搜索和会话分析功能。将其与 blackmount-nlp-mcp 搭配使用,可以分析你保存的对话:从聊天记录中提取关键词、评估 AI 回复的可读性、检测跨会话的情感趋势。

app.blackmount.ai — 完整的 Blackmount 平台。搜索、整理并分析你的 AI 工具产生的一切内容。


许可证

MIT

Install Server
A
license - permissive license
B
quality
A
maintenance

Maintenance

Maintainers
Response time
3dRelease cycle
2Releases (12mo)
Commit activity

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides token-efficient document search and retrieval for LLMs by returning relevant document sections within specified token budgets. It utilizes section-aware parsing and Bloom filter elimination to offer high-speed, zero-dependency access to large documents.
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Web content extraction for AI agents. 10 tools: scrape, crawl, map, batch, extract, summarize, diff, brand, search, research. Uses TLS fingerprinting to bypass anti-bot without a headless browser. Outputs LLM-optimized markdown with 67% fewer tokens than raw HTML.
    10
    2,292
    AGPL 3.0

View all related MCP servers

Related MCP Connectors

  • Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.

  • 16 AI-native tools with dual SSE + streamable-http transport. Free tier available.

  • Honest library picks for coding agents in 25-360 tokens. Tells your agent what NOT to install.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/BlackMount-ai/blackmount-nlp-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server