Capacities MCP Server
Enables search, content creation, weblink saving, and knowledge base analysis with Capacities through any MCP-compatible client.
README
Capacities MCP Server
An MCP server for Capacities — search, create content, save weblinks, and analyze your knowledge base from any MCP-compatible client.
Prerequisites
- A Capacities account with API access
- An API token (Capacities Desktop App → Settings → API → Generate token)
Installation
Choose the option that fits your setup:
Option 1: Claude Desktop Extension (Easiest)
- Download
capacities-desktop-extension.dxt - In Claude Desktop: Settings → Extensions → Import Extension
- Select the
.dxtfile and enter your API token when prompted
All dependencies are bundled — no additional setup needed.
Option 2: Run from Source
git clone https://github.com/inconceivablelabs/capacitiesMCP.git
cd capacitiesMCP
npm install
npm run build
Then add to your MCP client config (e.g. Claude Desktop's claude_desktop_config.json):
{
"mcpServers": {
"capacities": {
"command": "node",
"args": ["/path/to/capacitiesMCP/server/dist/index.js"],
"env": {
"CAPACITIES_API_TOKEN": "your_token_here"
}
}
}
}
Option 3: Docker Container
For running as a persistent service (e.g. behind an MCP gateway):
cd server
docker build -t capacities-mcp .
docker run -d \
-e CAPACITIES_API_TOKEN=your_token_here \
capacities-mcp
The Docker image uses server/ which contains only the runtime package and compiled output — no source or dev dependencies.
Available Tools
| Tool | Description |
|---|---|
search_content |
Search across Capacities spaces using keywords |
list_spaces |
List all your Capacities spaces |
get_space_info |
Detailed info about a specific space |
smart_search |
Context-aware search with related content |
advanced_search |
Search with date ranges, object types, and filters |
create_structured_note |
Create structured templates (meeting, daily-reflection, task-list, research) |
save_weblink |
Save a URL as a weblink with metadata and tags |
add_to_daily_note |
Add content to today's daily note |
analyze_content_patterns |
Analyze patterns in your content |
identify_knowledge_gaps |
Find underdeveloped topics |
Configuration
| Environment Variable | Required | Default |
|---|---|---|
CAPACITIES_API_TOKEN |
Yes | — |
CAPACITIES_API_BASE_URL |
No | https://api.capacities.io |
LOG_LEVEL |
No | info |
Project Structure
capacitiesMCP/
├── src/ # TypeScript source (single source of truth)
├── server/ # Runtime packaging
│ ├── Dockerfile # Container build
│ ├── package.json # Runtime dependencies only
│ └── dist/ # Compiled output (built from root src/)
├── tsconfig.json # Builds src/ → server/dist/
├── manifest.json # DXT extension manifest
└── *.dxt # Pre-built extension packages
npm run build compiles src/ directly into server/dist/. There is one source, one build step, and one output location used by all three installation methods.
Development
npm install
npm run build # Compile TypeScript
npm run dev # Watch mode
npm run inspector # MCP Inspector for debugging
npm test # Run tests
See CLAUDE.md for architecture details.
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。