hcom-mcp
A control-plane MCP server for launching and supervising hcom-managed agents, running as a single persistent HTTP server to coordinate multiple sessions.
README
hcom-mcp
Control-plane MCP server for launching and supervising hcom-managed agents.
Why HTTP, not stdio
MCP servers typically run over stdio — the client spawns one server process per session. For a control-plane server that manages a fleet of agents, that's a problem: ten terminal sessions spawn ten isolated MCP processes with no coordination between them.
hcom-mcp runs as a single persistent HTTP server. Every terminal session, every MCP client, every agent talks to the same endpoint. One process, one source of truth for launches, registries, and lifecycle.
Prerequisites
Install
git clone https://github.com/scchearn/hcom-mcp.git
cd hcom-mcp
npm install
npm run build
Run
Foreground (any OS)
HCOM_MCP_PORT=3111 node dist/index.js
Listens on http://127.0.0.1:3111/mcp. Only localhost connections are accepted.
As a daemon
| OS | Mechanism | Setup |
|---|---|---|
| Linux | systemd user service | cp docs/systemd/hcom-mcp.service ~/.config/systemd/user/ && systemctl --user enable --now hcom-mcp |
| macOS | launchd | cp docs/launchd/com.scchearn.hcom-mcp.plist ~/Library/LaunchAgents/ && launchctl load ~/Library/LaunchAgents/com.scchearn.hcom-mcp.plist |
| Windows | Task Scheduler or nssm | See docs/windows/hcom-mcp-task.xml for Task Scheduler, or the nssm commands in the file comments |
Adjust the ExecStart/ProgramArguments path in the config to match where you cloned the repo.
MCP client configuration
Point any HTTP-capable MCP client at http://127.0.0.1:3111/mcp. Example for Claude Desktop:
{
"mcpServers": {
"hcom-mcp": {
"type": "http",
"url": "http://127.0.0.1:3111/mcp"
}
}
}
Configuration
HCOM_MCP_PORT— HTTP port (default:3111)~/.hcom/mcp/config.json— presets, topologies, model catalogs~/.hcom/mcp/registry.json— managed agent registry.hcom-mcp.json— optional workspace overlay (see.hcom-mcp.example.json)
Skills
Install with:
npx skills add scchearn/hcom-mcp
Operating guidance ships in skills/:
skills/using-hcom/SKILL.md— messaging, threads, transcripts, event watchingskills/hcom-agent-messaging/SKILL.md— agent-to-agent messaging patterns and gotchas
Tools
| Tool | Purpose |
|---|---|
launch |
Launch a headless agent (preset or bare harness+model) |
launch_topology |
Launch multiple agents from a topology preset |
adopt |
Adopt an external hcom agent into managed lifecycle |
stop / kill |
Stop or kill a managed agent |
list_managed |
List agents managed by this server |
list_all |
List all live hcom agents |
list_models |
List available models per harness |
list_presets |
List configured agent presets |
list_topologies |
List configured topology presets |
inspect |
Inspect an agent's status, transcript, events, or terminal |
prune |
Remove stale registry records |
thread_seed |
Create a workflow thread |
thread_inspect |
Query thread events |
config_paths |
Show config and registry paths |
status |
Server health and orientation |
License
MIT
推荐服务器
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。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。