Attio MCP Server

A comprehensive Model Context Protocol (MCP) server for Attio, providing complete CRM surface coverage. This server enables AI assistants like Claude and ChatGPT to interact directly with your entire Attio workspace through natural language—manage Deals, Tasks, Lists, People, Companies, Records, and Notes without falling back to raw API calls.

🎯 What is Attio MCP Server?

Transform your CRM workflows with AI-powered automation. Instead of clicking through multiple screens, simply ask Claude or ChatGPT to find prospects, update records, manage pipelines, and analyze your data using natural language commands.

🎉 v1.0.0 Milestone: Complete Attio CRM surface coverage with full ChatGPT Developer Mode integration.

"Find all AI companies with 50+ employees that we haven't contacted in 30 days and add them to our Q1 outreach list"

🚀 NEW: ChatGPT Developer Mode Integration

v1.0.0 introduces full ChatGPT compatibility! ChatGPT Pro/Plus users can now access the entire Attio toolset through natural language via Smithery marketplace.

• 🔐 Built-in Approval Flows: MCP safety annotations auto-approve read operations, request approval for writes

• 🌐 OAuth Integration: Seamless authentication via https://server.smithery.ai/@kesslerio/attio-mcp-server/mcp

• 💬 Natural Language CRM: Manage your entire Attio workspace through conversational AI

• 📖 Setup Guide: See ChatGPT Developer Mode docs for complete configuration

✨ Core Features & Implementation Status

🎯 Universal Tools Architecture (14 Tools)

68% Tool Reduction: Consolidated 40+ resource-specific tools into 14 universal operations for consistent, powerful CRM management.

• High Performance: 89.7% speed improvement with 227KB memory reduction (PR #483)

• Enterprise Quality: 97.15/100 production readiness score with zero breaking changes

• Clean Architecture: Complete production-test separation with mock factory pattern

📊 Feature Implementation Status

✅ Complete CRM Surface Coverage

• Companies: Search, Create, Update, Delete, Advanced Search, Relationship Search

• People: Search, Create, Update, Delete, Advanced Search, Relationship Search

• Deals: Full CRUD operations with intelligent field mapping and stage validation

• Tasks: Create, Update, Delete, Search with multi-assignee support

• Lists: Full CRUD operations, filtering, advanced filtering, entry management

• Notes: Create and list operations for all record types

• Records: Universal CRUD operations across all resource types

• Batch Operations: Create, Update, Delete with chunking and error handling

• Content Search: Universal search capabilities across notes, tasks, and lists

• Relationship Navigation: Bidirectional company↔person↔deal relationships

• Advanced Filtering: Sophisticated query capabilities with intelligent field mapping

📊 Company Management

• Universal Search: Find companies with search-records and advanced-search

• Full CRUD: Create, read, update, and delete with universal record operations

• Relationship Discovery: Find companies through search-by-relationship

• Batch Operations: Process hundreds of companies with batch-operations

• Detailed Information: Get contact, business, and social info with get-detailed-info

👥 People Management

• Universal Contact Search: Find people by any criteria using universal search tools

• Relationship Tracking: Link people to companies with search-by-relationship

• Activity Timeline: Track interactions with search-by-content and search-by-timeframe

• Advanced Filtering: Multi-attribute search with universal filtering

• Bulk Operations: Efficiently manage contacts with universal batch operations

📋 Lists & Pipeline Management (11 Tools)

• Pipeline Operations: Move deals through sales stages

• Smart Segmentation: Create and manage targeted contact lists

• Advanced Filtering: Complex multi-condition filtering with AND/OR logic

• Entry Management: Add, remove, and update list memberships

• Deal Tracking: Monitor opportunities and revenue pipeline

• Deal Defaults: Configurable default stage, owner, and currency for streamlined deal creation

✅ Task Management

• Universal Task Operations: Create, update, and manage tasks with universal tools

• Record Linking: Associate tasks with any record type using resource_type parameter

• Progress Tracking: Monitor completion with universal search and filtering

• Team Coordination: Streamline follow-ups with consistent universal operations

🔧 Advanced Capabilities

• Batch Processing: Handle bulk operations with error tracking

• Enhanced Filtering: Text, numeric, date, boolean, and relationship filters with timeframe search (Issue #475)

• Data Export: JSON serialization for integrations

• Real-time Updates: Live data synchronization with Attio

💬 Pre-Built Prompts (10 Prompts)

Intelligent shortcuts that help Claude work faster with your CRM data:

• Search & Find (5): people_search, company_search, deal_search, meeting_prep, pipeline_health

• Take Actions (4): log_activity, create_task, advance_deal, add_to_list with dry-run safety

• Research & Qualify (1): qualify_lead with automated web research and BANT/CHAMP frameworks

• Token-efficient: 300-700 tokens per prompt with consistent formatting

• Discoverable: Claude automatically suggests relevant prompts for your tasks

See Using Out-of-the-Box Prompts for detailed documentation and examples.

🎯 Using Out-of-the-Box Prompts

NEW: 10 pre-built MCP prompts for common Sales workflows. No setup required—just use them!

Available Prompts

Quick Examples

Universal Arguments

All read prompts support:

• format: table | json | ids (default: table)

• fields_preset: sales_short | full (default: sales_short)

• verbosity: brief | normal (default: brief)

All write prompts support:

• dry_run: true | false (default: false) - Preview changes without executing

Token Awareness Features

Prompts include built-in token optimization:

• Budget Guards: Prompts stay within token limits (people_search <500, qualify_lead <400)

• Dev Metadata: Set MCP_DEV_META=true for token counts in responses

• Telemetry: Set PROMPT_TELEMETRY_ENABLED=true for usage logging

• Configurable Limits: Override with MAX_PROMPT_TOKENS environment variable

For complete prompt documentation, see docs/prompts/v1-catalog.md.

⚠️ Known Limitations & Important Notes

Current Limitations

• Field Parameter Filtering: Tasks endpoint /objects/tasks/attributes has limitations, handled with fallback patterns

• Pagination: Tasks pagination uses in-memory handling due to API constraints

API Compatibility

• Universal Tools: Primary interface (14 tools) - recommended for all new integrations

• Legacy Tools: Available via DISABLE_UNIVERSAL_TOOLS=true environment variable (deprecated)

• Lists API: Fully functional with complete CRUD operations (contrary to some outdated documentation)

🤝 OpenAI MCP Compatibility

• Developer Mode Ready: Every tool now publishes MCP safety annotations (readOnlyHint, destructiveHint) so OpenAI Developer Mode can auto-approve reads and request confirmation for writes.

• Search Compatibility Surface: The search and fetch tools remain available for OpenAI's baseline MCP support. Set ATTIO_MCP_TOOL_MODE=search to expose only these read-only endpoints (plus aaa-health-check) when Developer Mode is unavailable.

• Default Behaviour: With ATTIO_MCP_TOOL_MODE unset, the full universal tool set is exposed—matching Claude’s experience—while OpenAI users still see the compatibility wrappers.

• Detailed Guide: See docs/chatgpt-developer-mode.md for environment variables, approval flows, and validation tips.

• User Documentation: See the ChatGPT Developer Mode docs for a complete walkthrough of approval flows and setup instructions.

Performance Considerations

• Batch Operations: Optimized with chunking, rate limiting, and error recovery

• Large Datasets: Automatic pagination and field filtering for optimal performance

• Rate Limiting: Built-in protection against API rate limits with exponential backoff

For detailed troubleshooting and solutions, see TROUBLESHOOTING.md and GitHub Issues.

🎯 Mastering Advanced Search Filters

The Power Behind Precise CRM Queries - Stop wrestling with complex data searches. Our advanced filtering system lets you find exactly what you need with surgical precision.

"Find all AI companies with 50+ employees that we haven't contacted in 30 days and add them to our Q1 outreach list" - This kind of complex query is exactly what advanced search filters excel at.

🏗️ Filter Architecture

Every advanced search follows this proven pattern that's been battle-tested across thousands of CRM queries:

⚡ Real-World Examples

🔍 Single Criteria Search

🎯 Multi-Criteria Power Search (AND Logic)

🚀 Flexible OR Logic

🧠 Smart Filter Operators

💡 Pro Tips for Different Teams

🎯 Sales Teams - Use these field combinations:

• Companies: name, industry, employee_count, website, location

• People: full_name, job_title, email, company

📈 Marketing Teams - Focus on engagement fields:

• Activity tracking: last_interaction, email_status, campaign_response

• Segmentation: industry, company_size, location, engagement_score

✅ Customer Success - Monitor health metrics:

• Account health: renewal_date, support_tickets, usage_metrics

• Risk indicators: last_contact, satisfaction_score, contract_value

🚨 Avoid These Common Mistakes

❌ Wrong (Flat object structure):

✅ Correct (Nested array structure):

🔧 Quick Troubleshooting

Getting "Filters must include a 'filters' array property"?

1. ✅ Ensure your filters object contains a filters array

2. ✅ Each array item needs attribute, condition, and value

3. ✅ The attribute must be an object with a slug property

4. ✅ Double-check your JSON structure matches the examples above

💬 Pro Tip: Start with simple single-filter searches, then build complexity once you're comfortable with the structure.

🏆 Latest Updates - Critical Issues Resolved

✅ 100% Integration Test Pass Rate Achieved - All critical API contract violations and build issues have been resolved:

Recently Fixed Issues (August 2025)

• P0 Critical API Failures: Fixed response data structure handling for robust fallback patterns

• Build Compilation Errors: Created missing enhanced-validation module and resolved TypeScript compilation

• E2E Test Implementation: Fixed JSON truncation, resource mappings, and email validation consistency

• Field Parameter Filtering: Resolved tasks attribute handling with special case for missing /objects/tasks/attributes endpoint

• Email Validation Consistency: Fixed batch validation and create/update operation alignment

• Pagination System: Documented tasks pagination limitation with in-memory handling workaround

Test Status

• Integration Tests: 15/15 passing (100% pass rate)

• Build Status: All TypeScript compilation successful

• API Contract: All violations resolved with robust error handling

See TROUBLESHOOTING.md for detailed solutions to these resolved issues.

🚀 Installation

Installing via Smithery

To install Attio CRM Integration Server for Claude Desktop automatically via Smithery:

Option 1: NPM (Recommended)

Option 2: One-Command Script Installation

Option 3: Manual Installation

⚡ Quick Start

Prerequisites

• Node.js (v18 or higher)

• Attio API Key (Get one here)

• Attio Workspace ID

1. Set Environment Variables

2. Test the Installation

3. 🎯 CRITICAL: Configure Field Mappings

The MCP server uses field mapping files to translate between natural language and Attio's API field names. This configuration is essential for proper operation.

Quick Setup

Configuration Files (in configs/runtime/mappings/)

• default.json - Standard Attio CRM fields (loaded first, don't edit)

• sample.json - Examples with custom field templates (copy from this, not used at runtime)

• user.json - YOUR workspace-specific overrides (merged on top of default.json)

💡 Key Insight: user.json is merged on top of default.json, so only include overrides and additions. Don't duplicate mappings that already exist in default.json.

How Configuration Merging Works

The MCP server loads configuration in this order:

1. default.json - Contains all standard Attio fields (Name, Description, Team, etc.)

2. user.json - Your custom additions/overrides are merged on top

Example: If default.json has "Name": "name" and your user.json also has "Name": "name", that's wasted tokens. Only include fields that are:

• New custom fields (not in default.json)

• Different mappings (overriding default behavior)

Optimized user.json Example

✅ Good: Only custom/override fields
❌ Wasteful: Duplicating standard fields from default.json

⚠️ Without proper mapping configuration, the MCP server may not work correctly with your custom fields and lists.

Next: Verify your field mappings work by testing with Claude:

4. Configure Claude Desktop

Add to your Claude Desktop MCP configuration:

Finding Required IDs

Deal Owner Email (for deal owner defaults): The ATTIO_DEFAULT_DEAL_OWNER should be set to the email address of the workspace member who should own new deals by default. This is typically your own email address or the email address of your sales team lead.

Note: The system will automatically resolve email addresses to workspace member references when creating deals.

Deal Stages: Deal stages are specific to your workspace. Check your Attio workspace settings or use the discover-attributes command to find available stages for deals.

🌟 Example Use Cases

For Sales Teams

For Marketing Teams

For Customer Success

For Data Operations

🔐 Security & Privacy

• Secure API Authentication: Industry-standard API key authentication

• No Data Storage: Direct API passthrough with no local data retention

• Open Source: Full transparency with Apache 2.0 license

• Optional On-Premises: Deploy in your own infrastructure

📚 Documentation

Comprehensive documentation is available in the docs directory:

Universal Tools (Recommended)

⚠️ Note: Universal tools documentation is currently being updated to match the latest implementation. Use the API directly or check the source code for the most accurate interface definitions.

• API Overview - High-level API concepts and patterns

• Universal Tools Source - Current implementation reference

• Tool Schemas - Parameter definitions and validation

Getting Started

• Installation & Setup

• Claude Desktop Configuration

• Troubleshooting Guide

API Reference

📋 Implementation Status: These docs describe the Attio API endpoints. For MCP tool usage, refer to universal tools documentation above.

• API Overview - General Attio API concepts

• Companies API - Company record endpoints ✅ Fully Implemented via Universal Tools

• People API - Person record endpoints ✅ Fully Implemented via Universal Tools

• Lists API - List management endpoints ✅ Fully Implemented

• Notes API - Notes endpoints ✅ Basic Implementation

• Tasks API - Task endpoints ✅ Implemented via Universal Tools

Advanced Topics

• Batch Operations - Bulk operations ✅ Implemented with chunking

• Advanced Filtering - Complex queries ✅ Implemented

• Error Handling - Error patterns ✅ Enhanced error handling

• Extending MCP - Customization guide

Deployment

• Docker Guide

• Security Best Practices

🛠 Development

Setup Development Environment

Smithery CLI Development

For local development and testing with Smithery Playground:

See docs/deployment/smithery-cli-setup.md for detailed Smithery CLI development setup.

Testing

The project includes comprehensive testing at multiple levels with 100% E2E test pass rate:

🚀 E2E Test Framework (100% Pass Rate)

Our comprehensive E2E test framework validates all universal tools with real Attio API integration:

✅ Comprehensive Coverage:

• Pagination Testing: Validates offset parameter across all universal tools

• Field Filtering: Tests fields parameter for selective data retrieval

• Tasks Integration: Complete lifecycle testing for tasks resource type

• Cross-Resource Validation: Ensures consistent behavior across companies, people, lists, tasks

• Error Handling: Validates graceful error responses and edge cases

• Performance Monitoring: Tracks execution times and API response sizes

🛠️ Enhanced Assertions (7 New Methods):

📊 Performance Benchmarks:

• Search Operations: < 1000ms per API call

• CRUD Operations: < 1500ms per operation

• Batch Operations: < 3000ms for 10 records

• Field Filtering: < 500ms additional overhead

• Pagination: < 200ms additional per offset

Unit & Integration Tests

Test Environment Setup

For E2E and integration tests, you need:

1. Create in project root:

2. Verify API key format (must be exactly 64 characters)

3. Run tests to validate setup:

See the Testing Guide and E2E Troubleshooting Guide for detailed setup instructions.

Available Scripts

🤝 Contributing

We welcome contributions! Please see our Contributing Guidelines for details on:

• Adding new tools and features

• Improving documentation

• Reporting bugs and requesting features

• Testing and quality assurance

📈 What's Next?

This initial release provides a solid foundation for CRM automation.

🔗 Links

• NPM Package: https://www.npmjs.com/package/attio-mcp

• GitHub Repository: https://github.com/kesslerio/attio-mcp-server

• Issues & Support: https://github.com/kesslerio/attio-mcp-server/issues

• Releases: https://github.com/kesslerio/attio-mcp-server/releases

• Attio Documentation: https://developers.attio.com/

📄 License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Original Work Attribution: This project is based on initial work by @hmk under BSD-3-Clause license, with substantial modifications and enhancements by @kesslerio. The original BSD license notice is preserved in the LICENSE file as required.

Ready to transform your CRM workflow? Install Attio MCP Server today and experience the future of CRM automation with AI!