attio-mcp-server
Provides seamless access to the Attio API for AI assistants like Claude and Cursor, enabling interaction with objects, records, tasks, notes, and more through human-readable tools.
README
Attio MCP Server
A high-performance Model Context Protocol (MCP) server that provides seamless access to the Attio API, enabling AI assistants like Claude and Cursor to interact with your Attio workspace through human-readable tools.
Features
- 🏷️ Human-Readable Tool Names: Automatically transforms technical API names (like
getv2objects) into clear, categorized names (likelist_objects) - 📊 Full API Coverage: Access to objects, records, attributes, lists, tasks, notes, and more
- 📁 Organized by Category: Tools are grouped into logical categories for easy navigation
- 🤖 AI Assistant Ready: Works seamlessly with Claude Desktop and Cursor
- ⚡ High Performance: Built with Bun for fast execution and native TypeScript support
- 🔧 Easy Installation: Automated setup scripts with intelligent configuration detection
https://github.com/user-attachments/assets/c3a5fe4c-e97e-4bcb-8140-a88c712a35cd
Quick Start
-
Prerequisites:
# Install Bun (if not already installed) curl -fsSL https://bun.sh/install | bash -
Install and configure:
./install.sh -
Add your Attio access token to
.env:ATTIO_ACCESS_TOKEN=your_token_hereGet your token from: https://app.attio.com/settings/api
-
Restart Claude Desktop or Cursor
Manual Installation
For Claude Desktop
./install-claude.sh
This will automatically:
- Add the server to Claude's configuration
- Configure authentication with your access token
- Create a backup of existing configuration
For Cursor
./install-cursor.sh
This will automatically:
- Add the server to Cursor's settings
- Configure authentication with your access token
- Create a backup of existing settings
Available Tools
The MCP server exposes all Attio API endpoints as tools with human-readable names, organized by category:
Core Data Management
- Objects:
list_objects,create_object,get_object,update_object - Records:
list_records,create_record,query_records,delete_record - Attributes:
list_attributes,create_attribute,update_attribute_status
Lists & Entries
- Lists:
list_lists,create_list,update_list - List Entries:
create_list_entry,query_list_entries,update_list_entry
Collaboration
- Tasks:
list_tasks,create_task,update_task,delete_task - Notes:
list_notes,create_note,get_note,delete_note - Comments:
create_comment,get_comment,list_comment_threads
Administration
- Workspace:
list_workspace_members,get_workspace_member - Webhooks:
list_webhooks,create_webhook,update_webhook - Authentication:
get_current_user
Manual Testing
To test the server directly:
bun start
Configuration
The server uses the following environment variables:
ATTIO_ACCESS_TOKEN: Your Attio workspace access token (required)PORT: Port for web transport (default: 3000)LOG_LEVEL: Logging level (default: info)
Troubleshooting
-
Server not showing in Claude/Cursor:
- Restart the application after installation
- Check the logs for any errors
- Ensure the server is built:
bun run build
-
Authentication errors:
- Verify your access token in
.env - Ensure the token has the necessary permissions
- Verify your access token in
-
Build errors:
- Run
bun installto ensure all dependencies are installed - Run
bun run buildto compile TypeScript
- Run
Development
To modify the server:
- Edit
src/index.ts - Run
bun run build - Test with
bun test - Restart Claude/Cursor to load changes
Development Commands
# Install dependencies
bun install
# Build the server
bun run build
# Run tests
bun test
# Run tests with coverage
bun test --coverage
# Format and lint code
bun run check
# Manual testing
bun run test:manual
Support
For issues with:
- This MCP server: Create an issue in this repository
- Attio API: Contact support@attio.com
- MCP Protocol: Visit https://modelcontextprotocol.io
Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
License
This project is open source and available under the MIT License.
<div align="center"> <sub>Built with ❤️ for the AI community</sub> </div>
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。