官方说明7 个来源MCP 服务8 天前
Osseni94/keyneg-mcp
🐍 🏠 - Fine-grained sentiment analysis, keyword extraction and batch processing
在 GitHub 查看 ↗直链 · 无中转页
配置模板（请按你的客户端调整）
claude mcp add keyneg-mcp -- npx -y keyneg-mcp
这是根据仓库名生成的可粘贴骨架，命令行参数与包名请以该项目 README 为准。
- ★ 数取值
- 2 ★ · Osseni94/keyneg-mcp · 取自 GitHub 搜索 API · （2026-10-16 20:00:20 核对）
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-10-09 · 最近见到 2026-10-16 · 共见到 32 次 · 被 7 个来源列出
- 评分构成
- 综合分 703 · 2 ★ · 7 个来源 · mcp
常见问题（答案都来自我们的记录）
怎么安装？
我们【没有】从该仓库取到安装命令（我们的 install 覆盖率只有约 4%）。请看它的 README 或 releases 页。
它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
Osseni94/keyneg-mcp；我们收录于 2026-10-09；最近见到 2026-10-16。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。第三方质量标记
KeyNeg MCP Server
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
**The first general-purpose sentiment analysis tool for AI agents.**
KeyNeg MCP Server brings enterprise-grade sentiment analysis to Claude, ChatGPT, Gemini, and any AI assistant that supports the Model Context Protocol (MCP).
Features
- **95+ Sentiment Labels** - Comprehensive negative sentiment taxonomy
- **Keyword Extraction** - Identify specific complaints and issues
- **Batch Processing** - Analyze multiple texts efficiently
- **Tiered Access** - Free, Trial, Pro, and Enterprise tiers
- **Offline Capable** - No external API calls, runs locally
- **Fast** - Rust-powered inference via ONNX Runtime
Installation
Or install from source:
Prerequisites
1. **KeyNeg-RS** - The sentiment analysis engine:
2. **ONNX Model** - Export or download the model:
Configuration
Claude Desktop
Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json on macOS/Linux or %APPDATA%\Claude\claude_desktop_config.json on Windows):
Claude Code
Environment Variables
| Variable | Description | Default |
|----------|-------------|---------|
| KEYNEG_MODEL_PATH | Path to ONNX model directory | ~/.keyneg/models/all-mpnet-base-v2 |
| KEYNEG_LICENSE_KEY | License key for Pro/Enterprise | None (Free tier) |
Available Tools
analyze_sentiment
Analyze sentiment in text and return top sentiment labels with scores.
**Returns:**
extract_keywords
Extract negative keywords and phrases from text. *(Pro/Enterprise only)*
**Returns:**
full_analysis
Combined sentiment and keyword analysis.
**Returns:**
batch_analyze
Analyze multiple texts at once. *(Trial/Pro/Enterprise only)*
get_usage_info
Check your current tier and usage.
get_sentiment_labels
Get the full taxonomy of sentiment labels.
Pricing Tiers
| Tier | Price | Sentiment Labels | Keywords | Batch | Daily Calls |
|------|-------|------------------|----------|-------|-------------|
| **Free** | $0 | 3 | No | No | 100 |
| **Trial** | $0 (30 days) | 95+ | Yes | Yes | 1,000 |
| **Pro** | Contact us | 95+ | Yes | Yes | Unlimited |
| **Enterprise** | Contact us | 95+ | Yes | Yes | Unlimited |
Get a license at grandnasser.com
Use Cases
- **Customer Support** - Triage tickets by sentiment urgency
- **Content Moderation** - Flag negative/toxic content
- **HR Analytics** - Analyze employee feedback
- **Market Research** - Understand customer opinions
- **Social Listening** - Monitor brand sentiment
Example Prompts for Claude
Once configured, you can ask Claude things like:
KeyNeg MCP Server brings enterprise-grade sentiment analysis to Claude, ChatGPT, Gemini, and any AI assistant that supports the Model Context Protocol (MCP).
Features
- **95+ Sentiment Labels** - Comprehensive negative sentiment taxonomy
- **Keyword Extraction** - Identify specific complaints and issues
- **Batch Processing** - Analyze multiple texts efficiently
- **Tiered Access** - Free, Trial, Pro, and Enterprise tiers
- **Offline Capable** - No external API calls, runs locally
- **Fast** - Rust-powered inference via ONNX Runtime
Installation
Or install from source:
Prerequisites
1. **KeyNeg-RS** - The sentiment analysis engine:
2. **ONNX Model** - Export or download the model:
Configuration
Claude Desktop
Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json on macOS/Linux or %APPDATA%\Claude\claude_desktop_config.json on Windows):
Claude Code
Environment Variables
| Variable | Description | Default |
|----------|-------------|---------|
| KEYNEG_MODEL_PATH | Path to ONNX model directory | ~/.keyneg/models/all-mpnet-base-v2 |
| KEYNEG_LICENSE_KEY | License key for Pro/Enterprise | None (Free tier) |
Available Tools
analyze_sentiment
Analyze sentiment in text and return top sentiment labels with scores.
**Returns:**
extract_keywords
Extract negative keywords and phrases from text. *(Pro/Enterprise only)*
**Returns:**
full_analysis
Combined sentiment and keyword analysis.
**Returns:**
batch_analyze
Analyze multiple texts at once. *(Trial/Pro/Enterprise only)*
get_usage_info
Check your current tier and usage.
get_sentiment_labels
Get the full taxonomy of sentiment labels.
Pricing Tiers
| Tier | Price | Sentiment Labels | Keywords | Batch | Daily Calls |
|------|-------|------------------|----------|-------|-------------|
| **Free** | $0 | 3 | No | No | 100 |
| **Trial** | $0 (30 days) | 95+ | Yes | Yes | 1,000 |
| **Pro** | Contact us | 95+ | Yes | Yes | Unlimited |
| **Enterprise** | Contact us | 95+ | Yes | Yes | Unlimited |
Get a license at grandnasser.com
Use Cases
- **Customer Support** - Triage tickets by sentiment urgency
- **Content Moderation** - Flag negative/toxic content
- **HR Analytics** - Analyze employee feedback
- **Market Research** - Understand customer opinions
- **Social Listening** - Monitor brand sentiment
Example Prompts for Claude
Once configured, you can ask Claude things like:
- 来源
- awesome · https://github.com/Osseni94/keyneg-mcp
- 按领域浏览
- MCP 服务
- Traction
- 2 ★
- 收录于
- 昨天
更多MCP 服务
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。