#
ENJA

mcp-server

MCP Server

automanus-io/mcp-server

Deploy AI sales agents to WhatsApp and Webchat directly through AI assistants using the AutoManus Model Context Protocol server.

14 7MITUpdated 2026-03-11

Overview

The AutoManus MCP server allows users to instantly create, train, and deploy AI sales chatbots and customer service agents directly from tools like Claude Desktop, Cursor, or Claude Code. By providing a company website or natural language instructions, the server automatically researches the brand, populates a knowledge base, and provisions both WhatsApp numbers and embeddable webchat widgets.

Capabilities

  • Instant AI sales agent creation via natural language
  • Automated company website research and knowledge base population
  • Immediate deployment to WhatsApp and Webchat channels
  • Email-based agent claim link generation
  • API key integration for existing dashboard accounts

Best for

Quickly prototyping sales bots for startups, generating client chatbots for agencies, building e-commerce support assistants, and providing 24/7 automated lead qualification.

Works with

Claude CodeCursor
Evoa Score breakdown= Σ (score × weight)
69
Task usefulness20%88 → +17.6

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%85 → +12.8

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%70 → +10.5

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%28 → +3.4

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%75 → +7.5

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%37 → +3.0

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%50 → +2.5

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total69.2 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

The tool transmits user emails and communicates with external AutoManus APIs to provision cloud-hosted sales agents.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.