amoCRM MCP Server

amoCRM MCP Server

An MCP server that provides 36 tools for interacting with the amoCRM (Kommo) API v4, covering leads, contacts, companies, and tasks. It supports full entity lifecycles, account analytics, and bulk operations with integrated OAuth 2.0 and rate limiting.

Category
访问服务器

README

amoCRM MCP Server

MCP server for amoCRM (Kommo) API v4. Exposes 36 tools for leads, contacts, companies, tasks, notes, pipelines, associations, analytics, and more.

Built with FastMCP. Works with Claude Desktop, Cursor, and any MCP-compatible client.

Features

  • 36 MCP tools across 11 domains (leads, contacts, companies, tasks, notes, pipelines, associations, account, batch, unsorted, analytics)
  • OAuth 2.0 token refresh with disk persistence
  • Rate limiting — 7 req/s with automatic 429 backoff and jitter
  • HAL+JSON normalization — strips _links, flattens _embedded
  • Consistent response envelopes — {data, pagination} or {error, status_code, detail}
  • stdio and SSE transports

Quick Start

1. Install

pip install -e .

2. Configure

Copy .env.example to .env and fill in your amoCRM credentials:

cp .env.example .env

You need at minimum:

  • AMO_SUBDOMAIN — your amoCRM account subdomain
  • AMO_ACCESS_TOKEN — OAuth access token

For automatic token refresh, also set:

  • AMO_CLIENT_ID, AMO_CLIENT_SECRET, AMO_REFRESH_TOKEN

3. Run

# stdio (default — for Claude Desktop, Cursor, etc.)
python -m amocrm_mcp

# SSE transport
AMO_TRANSPORT=sse AMO_PORT=8000 python -m amocrm_mcp

Claude Desktop config

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "amocrm": {
      "command": "python",
      "args": ["-m", "amocrm_mcp"],
      "env": {
        "AMO_SUBDOMAIN": "your-subdomain",
        "AMO_ACCESS_TOKEN": "your-token"
      }
    }
  }
}

Tools

Domain Tools Description
Leads leads_list, leads_get, leads_search, leads_create, leads_create_complex, leads_update Full lead lifecycle
Contacts contacts_get, contacts_search, contacts_create, contacts_update Contact management
Companies companies_get, companies_search, companies_create, companies_update Company management
Tasks tasks_list, tasks_get, tasks_create, tasks_update CRM task operations
Notes notes_list, notes_create Notes on entities
Pipelines pipelines_list, pipelines_get, pipelines_list_statuses Pipeline & status info
Associations associations_get_linked, associations_link_entities Entity relationships
Account account_get, account_list_users, account_list_custom_fields Account metadata
Batch batch_create_leads, batch_create_contacts, batch_update_leads Bulk operations
Analytics analytics_get_events, analytics_get_pipeline_analytics, +1 CRM analytics
Unsorted unsorted_list, unsorted_accept, unsorted_reject Unsorted inbox

Getting amoCRM Credentials

  1. Go to your amoCRM account → Settings → Integrations
  2. Create a new integration (or use an existing one)
  3. Copy the access token, client ID, and client secret
  4. Your subdomain is the part before .amocrm.ru in your account URL

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选