Marvenn

Name: Marvenn
Author: marvennai

@marvennai

代码仓库

关于 Marvenn

Marvenn AI MCP server

#sales #crm #outreach #campaigns #leads #email #sdr #b2b #automation #marketing

基本信息

分类

其他

传输方式

stdio

发布者

marvennai

提交者

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "marvenn": {
      "command": "npx",
      "args": [
        "-y",
        "@marvenn/mcp-server"
      ],
      "env": {
        "MARVENN_API_KEY": "<your-api-key>",
        "MARVENN_BASE_URL": "https://marvenn.ai"
      }
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Marvenn?

The Marvenn MCP Server exposes the Marvenn AI-powered outreach and CRM platform to any MCP-compatible client (Claude Desktop, Continue, Cursor, etc.), enabling natural language interaction with campaigns, leads, pending actions, agents, and users.

How to use Marvenn?

Add the server to your MCP client’s configuration (e.g., Claude Desktop) using npx -y mcp-remote with the SSE endpoint https://marvenn.ai/mcp/sse and your API key as a Bearer token. Alternatively, open an SSE stream via curl and post JSON-RPC messages to the session-specific message URL.

Key features of Marvenn

Connect AI assistants to Marvenn CRM and outreach data
List and filter campaigns with status and stats
Search and paginate leads in the CRM
Approve or reject pending human-authorization actions
Manage AI agents, users, and credit balances
Transports: Streamable HTTP and SSE

Use cases of Marvenn

A sales manager asks an AI assistant to list all active campaigns and their performance stats
An outreach coordinator reviews and approves pending email or social actions via natural language
A team lead creates a new multi-channel outreach campaign from a chat prompt
An admin adjusts credit balances for users and filters users by subscription tier
A marketer searches leads by company name or status to find qualified prospects

FAQ from Marvenn

What transports does the Marvenn MCP Server support?

It supports Streamable HTTP (https://marvenn.ai/mcp) and SSE (https://marvenn.ai/mcp/sse), both marked as Working.

Is an API key required for all operations?

No. An API key is optional for discovery methods (tools/list, prompts/list, resources/list), but required for executing tools (tools/call).

What API key scopes are available?

Key scopes are read (read-only access), write (read plus creating campaigns and approving/rejecting actions), and admin (write plus user management and credit operations, also requires an admin account role).

How are scope errors reported?

Scope errors (e.g., using a read-only key to call a write tool) are returned as a tool result with an error field in the response body, not as a JSON-RPC protocol error.

What JSON-RPC error codes does the server return?

The server returns -32600 (invalid request), -32601 (method/tool not found), -32602 (invalid arguments), and -32603 (internal server error).

其他分类下的更多 MCP 服务器

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

ACI: Open-Source Infra to Power Unified MCP Servers

aipotheosis-labs

ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.