Mcp Agent Forge

Created By
HundunOnlinea year ago
A powerful MCP tool for forging and managing AI agent personalities with customizable expert traits and behaviors. 一个可以由大模型控制并定制Agent的MCP工具,supervisor架构,低成本复刻类似于CO-STORM的multi-agent research。
Overview

What is Mcp Agent Forge?

Mcp Agent Forge is a powerful tool for forging and managing AI agent personalities with customizable expert traits and behaviors, enabling users to create and simulate intelligent agents.

How to use Mcp Agent Forge?

To use Mcp Agent Forge, clone the repository from GitHub, build the project, and configure it with your DeepSeek API key. You can then create agents, simulate their responses, and manage them through various commands.

Key features of Mcp Agent Forge?

  • Agent Forging: Create agents with specific personality traits.
  • Thought Simulation: Simulate agent responses to questions.
  • Complete Management: Support for querying, listing, and deleting agents.
  • Multi-round Dialogue: Engage in deep multi-round conversations.
  • Natural Language Processing: Advanced language understanding capabilities based on DeepSeek API.

Use cases of Mcp Agent Forge?

  1. Creating expert agents for specific domains.
  2. Simulating conversations for research in multi-agent collaboration.
  3. Managing and adjusting agent behaviors for various applications.

FAQ from Mcp Agent Forge?

  • What are the system requirements?

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

  • Is there a demo available?

Yes! A demo application is available on Claude AI showcasing the capabilities of Agent Forge.

  • How can I contribute to the project?

Contributions are welcome in the form of new agent models, performance optimizations, documentation improvements, and bug fixes.

Server Config

{
  "mcpServers": {
    "mcp-agent-forge": {
      "command": "/path/to/mcp-agent-forge",
      "env": {
        "DEEPSEEK_API_KEY": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxx"
      }
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
HundunOnline
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago
Voyei

4 hours ago