Skip to main content
Glama
hara-lang

hara-mcp

Official
by hara-lang

hara-mcp

Hara 语言自有的 MCP 网关与执行主机协调。

架构与六阶段交付计划在 issue #1 中跟踪。当前实现切片为 issue #8

当前状态

本分支包含首个 MCP 与主机路由脚手架。它尚未提供生产端点,也未验证真实的 Hara 执行。确定性主机是一个默认禁用的传输夹具;在未打包的 Hara Chrome 主机于受限 Wasm Sandbox 中执行请求之前,Phase 1 仍保持开放。

Related MCP server: nodus-mcp-server

开发

需要 Node.js 22。

npm install
npm run check

启动未注册主机的 stdio 服务器:

npm run dev

仅为 MCP Inspector 开发启用确定性传输夹具:

HARA_MCP_ENABLE_TEST_FIXTURE=1 npm run dev

初始目录为:

hara_runtime_get
hara_eval
hara_call
hara_check

所有四个工具均声明为只读、非破坏性且封闭世界。没有选项启用浏览器、网络、持久文件系统、包、进程、提供者或外部效应权限。

边界

  • Hara 拥有执行语义以及规范的 Sandbox/LiveSession 生命周期。

  • Hara Chrome 是已注册的执行主机,而非 MCP 服务器。

  • mcp.greenways.ai 仍是 Greenways 应用入口,并在需要时直接消费底层 Hara 主机协议。

  • MCP 与主机/设备凭据在独立边界处终止。

修改前,请参阅 架构说明AGENTS.md

Install Server
A
license - permissive license
A
quality
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    B
    quality
    C
    maintenance
    A safety-first MCP operations cockpit for Hermes Agent installations, exposing typed, evidence-producing management primitives.
    73
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    A production-oriented MCP runtime providing orchestration tools for IDE and agent integrations, including task management, diagnostics, and token usage reporting.

View all related MCP servers

Related MCP Connectors

  • Hosted AgentLux MCP server for marketplace, identity, creator, services, and social flows.

  • A paid remote MCP for ZeroLang, built to return verdicts, receipts, usage logs, and audit-ready JSON

  • Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hara-lang/hara-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server