Atomic Crm MCP
A

Atomic Crm MCP

This is an MCP server designed for Atomic CRM that allows AI assistants to securely read and write data from CRM instances through secure OAuth 2.1 authentication and SQL query tools, and automatically enforces row-level security policies.
2.5 points
5.6K

What is the Atomic CRM MCP Server?

The Atomic CRM MCP Server is a bridge connecting AI assistants to Atomic CRM. It allows you to directly query and manipulate your CRM data in AI tools such as ChatGPT and Claude without leaving the conversation interface. The server uses secure OAuth authentication to ensure that only authorized users can access the data.

How to use the Atomic CRM MCP Server?

The usage process is divided into three main steps: 1) Set up the MCP server (locally or hosted); 2) Add the server connection in supported AI clients; 3) Authorize access through OAuth authentication. After authentication, you can directly query CRM data in AI conversations.

Applicable scenarios

It is suitable for scenarios that require quick querying of customer information, analysis of sales data, updating of contact records, etc. For example, you can ask the AI assistant: 'Find me the customers whose sales exceeded $10,000 last month', or 'Update Zhang San's contact phone number'.

Main features

Secure OAuth 2.1 authentication
Use the enterprise-level OAuth authentication provided by Supabase to ensure that only authorized users can access CRM data. The authentication process complies with the latest security standards.
SQL query execution
Execute SQL queries directly through the AI assistant, supporting complex queries including JOIN operations to flexibly obtain the required data.
Row-level security protection
All queries automatically apply row-level security policies to ensure that users can only access the data they have permission to access.
Multi-client support
Supports multiple AI clients such as ChatGPT, Claude, and VS Code, covering desktop and mobile usage scenarios.
Database schema query
Provides tools to obtain the database schema to help the AI assistant understand the data structure and generate accurate query statements.
Advantages
Seamless integration: Directly operate CRM data in AI conversations without switching applications
Enterprise-level security: OAuth 2.1 authentication and row-level security protection ensure data security
Flexible query: Supports complex SQL queries to meet various data analysis needs
Multi-platform support: Compatible with mainstream AI assistants and development tools
Easy to deploy: Provides both local and hosted deployment methods
Limitations
Requires a paid AI account: Both ChatGPT and Claude require a paid account to use the custom connector
Technical dependency: Requires Supabase as the backend infrastructure
Deployment complexity: Local deployment requires tools such as ngrok
Network requirements: The hosted server must support IPv6 connections
Learning curve: Non-technical users may need help to complete the initial setup

How to use

Environment preparation
Clone the code repository, install dependencies, and configure the environment variable file.
Supabase configuration
Enable the OAuth 2.1 server in the Supabase console, configure the JWT signing key, and obtain database connection information.
Server deployment
Choose local deployment (using ngrok) or hosted deployment to a server that supports IPv6.
Client connection
Add the MCP server connection in ChatGPT, Claude, or VS Code, and authorize access using OAuth authentication.
Start using
After successful authentication, you can query and manipulate CRM data in AI conversations.

Usage examples

Customer data analysis
The sales manager needs to quickly understand the performance of customers this quarter and queries relevant data through the AI assistant.
Contact information update
The customer service staff needs to update the contact information of customers and completes it through natural language instructions.
Sales report generation
The management needs a monthly sales report and aggregates data through the AI assistant.

Frequently Asked Questions

Why does the connection to the MCP server fail?
What should I do if the database connection fails?
What is the reason for the query being denied access?
Which AI clients are supported?
Is a paid account required?

Related resources

MCP Protocol Specification
Official documentation and specification of the Model Context Protocol
MCP Authorization Guide
Guide to implementing MCP security authorization
Supabase OAuth Server
Configuration documentation for the Supabase OAuth server
Atomic CRM
Official website of Atomic CRM
GitHub Repository
Project source code and latest updates

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
9.6K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.2K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
14.9K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.7K
4 points
P
Paperbanana
Python
10.0K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
8.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
10.0K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
8.9K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
28.5K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
81.7K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
38.2K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.9K
4.5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
69.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
37.5K
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
56.5K
4.8 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
106.3K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase