広告掲載
MCP.so
ログイン

MCP Agent Forge

@HundunOnline

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

HundunOnline

投稿者

Alfred Xia

MCP Agent Forge について

A powerful MCP tool for forging and managing AI agent personalities with customizable expert traits and behaviors.

#agent-making#build-multi-agent

MCP Agent Forge の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-agent-forge": {
      "command": "/path/to/mcp-agent-forge",
      "env": {
        "DEEPSEEK_API_KEY": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxx"
      }
    }
  }
}

MCP Agent Forge のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Mcp Agent Forge?

Mcp Agent Forge is a platform for creating and managing AI agents with specific personality traits, simulating their responses to questions, and building multi-agent collaboration research projects similar to CO-STORM. It uses the DeepSeek API for advanced language understanding.

How to use Mcp Agent Forge?

Install Go 1.24.1+, clone the repository, and run make build. Configure the MCP server in your client’s settings by setting the DEEPSEEK_API_KEY environment variable. Invoke tools such as expert_personality_generation to create agents, agent_answer to simulate responses, get_agent, list_agents, and delete_agent for management.

Key features of Mcp Agent Forge

  • Create agents with specific personality traits
  • Simulate agent responses to questions
  • Query, list, and delete agents
  • Support deep multi-round conversation interactions
  • Advanced language understanding powered by DeepSeek API

Use cases of Mcp Agent Forge

  • Building multi-agent research projects similar to CO-STORM
  • Creating expert agents with professional backgrounds for Q&A
  • Conducting multi-round dialogues with simulated experts
  • Managing and adjusting agent behavior over time

よくある質問

1

What are the system requirements?

Go 1.24.1 or higher and a DeepSeek API key are required.

2

How do I configure Mcp Agent Forge?

Set the `DEEPSEEK_API_KEY` environment variable (required) and optionally configure `LOG_LEVEL`, `LOG_PATH`, `CONFIG_PATH`, `PORT`, and `DEBUG`.

3

What tools does Mcp Agent Forge provide?

Five tools: `expert_personality_generation` (create an agent), `agent_answer` (simulate a response), `get_agent` (get agent info), `list_agents` (list all agents), and `delete_agent` (remove an agent).

4

Can agents engage in multi-turn conversations?

Yes. The `agent_answer` tool supports a `planned_rounds` and `current_round` parameter to manage multi-round dialogues.

5

How are agent personalities customized?

When creating an agent via `expert_personality_generation`, you provide an `agent_name` and a comma-separated list of `core_traits` (e.g., “Systems Thinking, First Principles”).

コメント

「AI とエージェント」の他のコンテンツ

BlazingCDN MCP - Content Delivery for Video, Software & Static Files

BlazingCDN

Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN

1

Ads Uploader — Meta Ads MCP

Ads Uploader

Launch Meta ads with your AI agent. Bulk-create Facebook and Instagram ads, import Google Drive creatives, launch partnership ads with authorized creators, and review saved builds before launch.

PDI Bridge for Claude

jxrlabs

Connect Claude Desktop to your ServiceNow PDI. Query records, inspect Business Rules, review ACLs, and troubleshoot against your live instance.

hausverbot

eliduarte37

BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude

HeyLead: LinkedIn Outreach & Lead Generation MCP Server

D4umak

HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.

9
広告掲載