MCP Suite CRM
Enables AI agents to interact with a CRM covering companies, people, leads, deals, and more, with role checks, scoped agent keys, approval gates, and a shared audit trail.
README
MCP Suite CRM
An open-source CRM built for humans and AI agents to operate together. The web application and every MCP client use the same typed operation catalog, with role checks, scoped agent keys, approval gates for risky agent actions, and a shared audit trail.
Pre-release: the source is public, but the supported installer, npm package, container image, and stable release are not published yet.
What is included
| Path | Purpose |
|---|---|
apps/web |
Login, the authenticated CRM under /app/*, and the HTTP operation API |
apps/mcp |
MCP over stdio and HTTP |
packages/core |
Domain types, authorization policy, and operation catalog |
packages/db |
SQLite persistence, schema, authentication, and bootstrap |
The CRM covers companies, people, leads, deals, activities, tasks, pipelines, tags, contact lists, custom fields, saved views, offerings, approvals, users, agents, and audit events. The public marketing site, signup, billing, and managed-hosting controls are deliberately not part of this repository.
Run from source
The supported development platform is 64-bit Linux. Install mise; the repository pins Node 22 and pnpm 10.
mise trust
mise exec -- make setup
mise exec -- make dev
Open http://localhost:2222. / redirects to /login. The first setup creates
the SQLite database at data/emcp.db and prints the initial owner credentials;
change the password after signing in.
Run with Docker
docker compose up -d
One container, one process on :2222: the web app, the operation API, the
MCP endpoint for agents (POST /mcp) and GET /healthz. Persistent state
lives in ./data. The compose file builds the mcpsuite/crm image locally
until official images are released. See PRODUCTION.md for
the standalone-MCP command override and reverse-proxy guidance.
Connect an agent
In the CRM, open Admin → Agents, create an agent client, and copy the key shown once. The UI provides a ready-to-paste configuration. The full transport, scope, and trust-profile guide is in docs/mcp.md.
Example for Claude Code:
claude mcp add --transport http mcpsuite-crm http://localhost:2222/mcp \
--header "Authorization: Bearer emcp_YOUR_KEY"
Development checks
mise exec -- make typecheck
mise exec -- make test
mise exec -- make build
mise exec -- make smoke
See AGENTS.md for the code architecture and conventions, PRODUCTION.md for the current self-hosting runbook, and CONTRIBUTING.md before opening a pull request.
License
AGPL-3.0-only. See LICENSE.
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。