ferodrigop/forge
Terminal MCP server for AI coding agents — spawn, manage, and monitor PTY sessions via the Model Context Protocol
Platform-specific configuration:
{
"mcpServers": {
"forge": {
"command": "npx",
"args": [
"-y",
"forge"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> </p>
<h1 align="center">Forge</h1>
<p align="center"> Terminal MCP server for AI coding agents. Spawn, manage, and monitor real PTY sessions via the Model Context Protocol. </p>
<p align="center"> <a href="https://forgemcp.dev"><strong>forgemcp.dev</strong></a> </p>
<p align="center"> <a href="https://www.npmjs.com/package/forge-terminal-mcp"></a> <a href="https://github.com/ferodrigop/forge/actions/workflows/ci.yml"></a> <a href="https://www.npmjs.com/package/forge-terminal-mcp"></a> </p>
---
<p align="center"> </p>
<p align="center"> </p> <p align="center"> </p>
AI coding agents (Claude Code, Codex, etc.) typically run one command at a time. Forge gives them persistent terminals — run your React frontend, Java API, and Postgres migrations in parallel, monitor all three, and only read what changed. Full-stack work without the bottleneck.
Works with any MCP-compatible client — Claude Code, Codex, or your own agent.
Key differentiators:
node-pty (same lib as VS Code terminal) — interactive programs, colors, TUI apps all workread_terminal only returns NEW output, saving context window tokensLoading reviews...