Attio MCP Server
A comprehensive Model Context Protocol (MCP) server for Attio, enabling AI assistants like Claude to interact with your CRM through natural language.
Transform your CRM workflows: "Find all AI companies with 50+ employees that we haven't contacted in 30 days"
✨ Key Features
- Universal Tools: 13 tools work across all record types (companies, people, deals, lists, tasks)
- High Performance: 89.7% speed improvement with 227KB memory reduction (PR #483)
- Natural Language: Search, create, update, and manage CRM data conversationally
- Advanced Filtering: Complex multi-condition searches with relationship-based queries
- Batch Operations: Process hundreds of records efficiently with optimized formatResult architecture
- Full CRUD: Complete create, read, update, delete capabilities for all record types
- Field Mapping Excellence: Corrected field mappings with category validation and special character preservation
- Enterprise Quality: 97.15/100 production readiness score with zero breaking changes
- Clean Architecture: Complete production-test separation with mock factory pattern
🚀 Quick Start
Installation
Configuration
- Get your Attio API key: Attio Developer Documentation
- Configure environment:
- Add to Claude Desktop (
~/Library/Application Support/Claude/claude_desktop_config.json
):
💬 Example Usage
Once configured, interact with your Attio CRM naturally:
📚 Documentation
- Getting Started - Detailed setup and installation
- User Guide - Common workflows and examples
- API Reference - Complete tool documentation
- Field Mapping Guide - Field validation, categories, and special characters
- Deployment - Docker and production deployment
- Development - Contributing and extending
🔧 Core Tools
Tool | Purpose |
---|---|
search-records | Find any record type with flexible criteria |
get-record-details | Retrieve complete record information |
create-record | Create companies, people, deals, tasks, etc. |
update-record | Modify existing records |
delete-record | Remove records safely |
advanced-search | Complex multi-condition filtering |
batch-operations | Process multiple records efficiently |
⚡ Performance & Architecture
Recent Improvements (PR #483)
Our formatResult architecture refactoring delivered exceptional performance gains:
- 89.7% faster execution - Optimized string formatting eliminates environment detection overhead
- 227KB memory reduction - Efficient memory management with 57.8% fewer object allocations
- 59% code quality improvement - ESLint warnings reduced from 957 to 395
- 100% type safety - Eliminated dual return types and environment-dependent behavior
- Zero breaking changes - Complete backward compatibility maintained
Architecture Excellence
- Clean Separation: Complete production-test isolation with mock factory pattern
- Mock Factory Architecture: Centralized test data generation for Issue #480 compatibility
- Environment Independence: No runtime behavior changes based on NODE_ENV
- Type Safety: Consistent string return types across all formatResult functions
See our Performance Report and Architecture Guide for technical details.
🐳 Docker Deployment
🧪 Testing
The project maintains high-quality test coverage with modern mock factory architecture:
- E2E Tests: 76% success rate (29/38 passing) with Issue #480 compatibility
- Integration Tests: 100% success rate with real API validation
- Unit Tests: 100% success rate (26/26 passing) with clean architecture
- Performance Tests: Environment-aware budgets with dual testing strategy
- Mock Factory Pattern: Complete production-test separation for reliable testing
See our Testing Guide, Mock Factory Pattern, and Production-Test Separation for details.
🤝 Contributing
We welcome contributions! See our Contributing Guide for details on:
- Setting up the development environment
- Running tests and linting
- Submitting pull requests
- Code standards and best practices
📄 License
This project is licensed under the Apache License 2.0. See LICENSE for details.
🔗 Links
- Documentation: Full Documentation
- Issues: Report bugs or request features
- Smithery: Install via Smithery
- Attio: Learn more about Attio CRM
Need help? Check our troubleshooting guide or open an issue.
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
A Model Context Protocol server that enables AI assistants like Claude to interact directly with Attio CRM data, supporting operations for companies, people, lists, and tasks through natural language queries.
Related MCP Servers
- -securityAlicense-qualityA Model Context Protocol server that connects Claude and other MCP clients to Aider, enabling AI assistants to efficiently edit files, create new files, and interact with git repositories through natural language.Last updated -34PythonThe Unlicense
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants like Claude to interact directly with Home Assistant, allowing them to query device states, control smart home entities, and perform automation tasks.Last updated -12152PythonMIT License
- AsecurityFlicenseAqualityA Model Context Protocol server that connects AI assistants like Claude to Notion workspaces, enabling them to view, search, create, and update Notion databases, pages, and content blocks.Last updated -129071JavaScript
- AsecurityFlicenseAqualityA Model Context Protocol server that enables AI assistants like Claude to access and search Atlassian Confluence content, allowing integration with your organization's knowledge base.Last updated -755624TypeScript