Instagram DM Server for AI Assistants

Created By

KynuxDeva month ago

Read, send, search, and manage Instagram Direct Messages through AI assistants via MCP. 15 tools including inbox, send, search, react, and thread management. Cookie-based auth, single dependency, TypeScript strict, auto-pagination.

# instagram

# dm

Overview Content Tools Comments

Content

MCP Instagram DM

Control your Instagram DMs with AI. Read, send, search, and manage Instagram Direct Messages through natural language with any MCP-compatible AI assistant.

Features

15 tools across three categories:

Read & Monitor

instagram_get_inbox — List DM conversations with unread/group/muted indicators
instagram_get_thread — Get messages (auto-paginates 500+ messages)
instagram_get_pending — List pending DM requests
instagram_user_info — Get any user's profile
instagram_thread_info — Thread metadata and participants

Send & Manage

instagram_send_message — Send text messages
instagram_send_link — Share URLs with optional caption
instagram_create_thread — Start new DMs with one or multiple users
instagram_like_message — React with any emoji
instagram_unsend_message — Unsend your messages
instagram_mark_seen — Mark conversations as read
instagram_approve_pending — Approve pending requests

Search & Discover

instagram_search_inbox — Search conversations by username
instagram_search_messages — Find messages containing specific text
instagram_search_users — Search Instagram users

Quick Start

npx mcp-instagram-dm

Setup takes 60 seconds: grab 3 cookies from Chrome DevTools, add to your MCP config, done.

Design Principles

Single dependency — only @modelcontextprotocol/sdk
TypeScript strict — zero any types
Auto-pagination — fetch 500+ messages with rate limiting
14+ message types — text, media, voice, reels, GIFs, stories, and more
Cookie-based auth — no API keys, no OAuth

Server Config

{
  "mcpServers": {
    "instagram": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-instagram-dm"
      ],
      "env": {
        "INSTAGRAM_SESSION_ID": "your_session_id",
        "INSTAGRAM_CSRF_TOKEN": "your_csrf_token",
        "INSTAGRAM_DS_USER_ID": "your_user_id"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

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。

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

CursorThe AI Code Editor

Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.

Tavily Mcp

Amap Maps高德地图官方 MCP Server

Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.