Fireberry CRM MCP Server
Enables AI assistants to securely interact with Fireberry CRM, allowing metadata exploration, schema management, and record operations through natural language.
README
Fireberry CRM MCP Server
<a target="_blank" href="https://fireberry.com" align="center" style="filter:drop-shadow(0 0 18px #fff) drop-shadow(0 0 12px #fff)"> <img alt="Fireberry's Logo" src="./docs/fireberry-logo.svg">
</a>
A powerful Model Context Protocol (MCP) server for seamless AI-CRM integration
</div>
Connect your AI assistants directly to Fireberry CRM with secure, real-time access to your customer data. Perform complex CRM operations through natural language interactions.
Quick Start
1. Get Your API Token
Generate your Fireberry API token following the authentication guide.
2. Install & Configure
Choose your preferred runtime:
Node.js (Recommended)
Add to your MCP configuration file:
{
"mcpServers": {
"fireberry-crm": {
"command": "npx",
"args": ["-y", "@fireberry/mcp-server@latest"],
"env": {
"FIREBERRY_TOKEN_ID": "<your-token-here>"
}
}
}
}
Bun
{
"mcpServers": {
"fireberry-crm": {
"command": "bunx",
"args": ["@fireberry/mcp-server@latest"],
"env": {
"FIREBERRY_TOKEN_ID": "<your-token-here>"
}
}
}
}
3. Tool-Specific Setup
<details> <summary><strong>Claude Desktop</strong></summary>
Update claude_desktop_config.json from MCP official docs:
{
"mcpServers": {
"fireberry-crm": {
"command": "npx",
"args": ["-y", "@fireberry/mcp-server@latest"],
"env": {
"FIREBERRY_TOKEN_ID": "<your-token-here>"
}
}
}
}
</details>
<details> <summary><strong>VS Code (GitHub Copilot)</strong></summary>
Add to .vscode/settings.json:
{
"github.copilot.advanced": {
"mcpServers": {
"fireberry-crm": {
"command": "npx",
"args": ["-y", "@fireberry/mcp-server@latest"],
"env": {
"FIREBERRY_TOKEN_ID": "<your-token-here>"
}
}
}
}
}
</details>
<details> <summary><strong>Cursor</strong></summary>
Navigate to Settings → MCP Servers and add:
{
"fireberry-crm": {
"command": "npx",
"args": ["-y", "@fireberry/mcp-server@latest"],
"env": {
"FIREBERRY_TOKEN_ID": "<your-token-here>"
}
}
}
</details>
Features
🔍 Metadata & Discovery
metadata_objects— List all available CRM object typesmetadata_fields— Get field definitions for any object typemetadata_picklist— Retrieve picklist values and options
🏗️ Schema Management
object_create— Create new custom objectsfield_create— Add custom fields to existing objects
📝 Record Operations
record_create— Create new records for any object typerecord_update— Update existing records with new values
Usage Examples
Once configured, try these natural language prompts:
Exploring Your Fireberry platform
"What object types are available in my Fireberry CRM?"
"Show me all fields for the Contacts object"
"List the picklist values for the Account Status field"
Data Operations
"Create a new custom object called 'Projects' with description, and status fields"
"Add a 'Project Budget' currency field to the Projects object"
"Create a new project record called 'Q1 Digital Transformation'"
"Import this contacts.csv file into my CRM"
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
FIREBERRY_TOKEN_ID |
✅ | Your Fireberry API token |
Security
- 🔐 All requests authenticated with your Fireberry API token
- 🔑 Token validation on startup
Troubleshooting
Common Issues
Server not starting?
- Verify your
FIREBERRY_TOKEN_IDis correct - Check that Node.js/Bun is properly installed
- Ensure network connectivity to
api.fireberry.com
Tools not appearing?
- Restart your AI assistant after configuration
- Verify JSON syntax in configuration files
- Check MCP server logs for error messages
Development Setup
git clone https://github.com/fireberry/mcp-server
cd mcp-server
npm install
npm run dev
License
MIT License - see LICENSE file for details.
<div align="center"> Made with ❤️🔥 by the <a href="https://fireberry.com">Fireberry</a> team </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。