Massed Compute Mcp

MCP开发工具

提供方 Massed-Compute

开发工具 HTTP · 远程 API Key 社区 / 第三方 Claude DesktopClaudeCursorCodex
查看接入方式

Model Context Protocol server for Massed Compute — list GPU inventory, launch and manage VM instances, manage SSH keys, audit billing.

一句话选型结论

按资料字段整理

Massed Compute Mcp 属于开发工具类 MCP 服务器,HTTP · 远程,API Key,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接复制的远程端点配置。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式HTTP · 远程 鉴权API Key 部署方式远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

gpucloudinfrastructure

安装与配置

HTTP · 远程 API Key
连远程 HTTPS 端点,通常为 Streamable HTTP
https://vm.massedcompute.com/api/mcp

把它填进客户端的 MCP 配置即可,不需要在本地安装运行时。

  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Massed Compute Mcp当前 未标注 HTTP · 远程 远程部署 有 未标注
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Massed-Compute上游标注的维护方 Massed-Compute
分类开发工具本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · node本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

6.8 KB
来自项目仓库与上游目录的原文,未做删改

Massed Compute MCP Server

A Model Context Protocol server that lets AI assistants — Claude, Cursor, Codex, ChatGPT, and other MCP-compatible clients — interact with your Massed Compute account: browse GPU inventory, launch and manage VMs, audit billing, discover setup recipes.

Contents

  • Overview
  • Installation
  • Verifying the connection
  • CLI reference
  • Key resolution
  • Resources
  • License

Overview

The packages published from this repo are a verbatim proxy of the public MCP endpoint at https://vm.massedcompute.com/api/mcp — zero added surface. Every JSON-RPC message (initialize, tools/list, tools/call, resources/list, resources/read, ping, …) is forwarded unchanged with your stored API key injected as a Bearer header, and responses come back unchanged. Nothing is added, renamed, filtered, or rewritten on the way through:

  • The hosted endpoint owns the catalog. Tools, resources, schemas, and descriptions come from the live endpoint — the local package never goes stale when new capabilities (like setup recipes) ship upstream.
  • The hosted endpoint owns security. Key-scope enforcement (read-only keys hide destructive tools) and credential redaction happen server-side, identically for every client.
  • What the local package adds is exactly what a stdio client needs: a stdio↔streamable-HTTP bridge, OS-conventional storage for your API key (0600 on POSIX), and one-shot client wiring via init.

Issue a read-only key for analysis-only assistants and the endpoint rejects destructive tool calls (launch, restart, terminate, SSH-key changes) at call time. Works with Claude Code, Claude Desktop, Cursor, and Codex. Run massed-compute-mcp tools to print the live catalog — GPU inventory, VM images, instance lifecycle, coupons, billing, SSH keys, and setup recipes.

Beyond raw tools, Massed Compute publishes Agent Skills — markdown workflow templates for common operations like GPU selection and cost auditing. Full docs at vm-docs.massedcompute.com/docs/category/mcp.

Installation

Step 1. Get your API key

Open vm.massedcompute.com/settings/api, create a key (read-only for analysis-only assistants; full-access to allow launch / restart / terminate / SSH-key changes), copy it.

Step 2. Pick an install path

  • Hosted endpoint — point your client at the streamable-HTTP URL, zero install
  • Local CLI — runs on your machine, key stored in your OS config dir

Hosted endpoint

The local packages proxy this endpoint verbatim, so pointing your client straight at it gives you the identical catalog with nothing to install. Pick the snippet for your client:

Claude Code```bash
claude mcp add --transport http massed-compute \
https://vm.massedcompute.com/api/mcp \
--header "Authorization: Bearer MC_TOKEN"


**Cursor** — `~/.cursor/mcp.json````json
{
  "mcpServers": {
    "massed-compute": {
      "url": "https://vm.massedcompute.com/api/mcp",
      "headers": { "Authorization": "Bearer MC_TOKEN" }
    }
  }
}

Codex — `~/.codex/config.toml````toml
[mcp_servers.massed-compute]
url = "https://vm.massedcompute.com/api/mcp"
bearer_token_env_var = "MC_TOKEN"
enabled = true


**Claude Desktop**

Claude Desktop does not yet speak streamable-HTTP MCP, so use `mcp-remote` as a stdio↔HTTP bridge. Config at `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):```json
{
  "mcpServers": {
    "massed-compute": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://vm.massedcompute.com/api/mcp",
        "--header", "Authorization: Bearer MC_TOKEN"
      ]
    }
  }
}

Local CLI

Install via whichever ecosystem you prefer:```bash
npm install -g massed-compute-mcp # Node >= 20

or

pip install massed-compute-mcp # Python >= 3.10

or

uv tool install massed-compute-mcp # fast Python install via uv


Run one-shot setup:```bash
massed-compute-mcp init

init prompts for the key, validates it upstream, stores it at 0600 (POSIX), detects installed MCP clients (Claude Code, Cursor, Claude Desktop, Codex), and offers to wire each one. A timestamped backup is taken before any client edit. Restart wired clients to pick up the tools.

Config file location:

  • Linux: $XDG_CONFIG_HOME/massed-compute/config.json (falls back to ~/.config/...)
  • macOS: ~/Library/Application Support/massed-compute/config.json
  • Windows: %APPDATA%\massed-compute\config.json

Non-interactive (CI / scripts):```bash

Key from env, auto-wire every detected client

MASSED_COMPUTE_API_KEY=<your-key> massed-compute-mcp init --yes

Key from a file, wire only specific clients

massed-compute-mcp init --token-file ~/keys/mc --yes --clients claude-code,cursor

Store the key only; don't touch any client config

massed-compute-mcp init --yes --no-install-clients


Add or remove a client later:```bash
massed-compute-mcp install-client cursor       # claude-desktop | codex | claude-code
massed-compute-mcp uninstall-client cursor

install-client is idempotent — re-running when the entry already matches is a silent no-op.

Verifying the connection```bash

massed-compute-mcp doctor
```

doctor confirms the stored key still works, prints the tool catalog, and shows copy-pasteable snippets for any clients you didn't auto-wire. Or just ask your assistant "Validate my Massed Compute API key." — a { message: &quot;Valid Token&quot; } response confirms the wiring.

CLI reference

Command What it does
massed-compute-mcp (no args) Run the MCP server over stdio
massed-compute-mcp init First-run setup: prompt, validate, store, wire clients
massed-compute-mcp doctor Verify the stored key and print client snippets
massed-compute-mcp install-client Wire a single client (claude-code, cursor, claude-desktop, codex)
massed-compute-mcp uninstall-client Remove our entry from a client config
massed-compute-mcp config show Print resolved config path, masked key, resolution chain
massed-compute-mcp logout Delete the stored API key
massed-compute-mcp tools [--json] Fetch and print the live tool catalog from the hosted endpoint
massed-compute-mcp version Print the version

Key resolution

When the server starts, the API key is taken from the first source that provides one:

  1. --token CLI flag
  2. --token-file CLI flag (first line, trimmed)
  3. MASSED_COMPUTE_API_KEY environment variable
  4. Stored config file written by init

If none of those are set, the server exits non-zero with a pointer to massed-compute-mcp init. Override the upstream with MASSED_COMPUTE_API_BASE_URL (default https://vm.massedcompute.com).

Resources

  • Full MCP documentation
  • Massed Compute API reference
  • Massed Compute console
  • Model Context Protocol spec

License

MIT — see LICENSE.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Massed Compute Mcp 怎么安装?

在客户端按下面的安装命令接入:https://vm.massedcompute.com/api/mcp。装完在客户端配置里引用同一个包或端点。

Massed Compute Mcp 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是HTTP · 远程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Massed Compute Mcp 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Massed Compute Mcp 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

Massed Compute Mcp 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Massed Compute Mcp 能提供哪些能力?

资料显示能力标签包括 gpu、cloud、infrastructure。具体工具清单以官方文档为准。

Massed Compute Mcp 需要什么运行环境?

运行时为 node;属于远程端点,不需要在本地装运行时。

Massed Compute Mcp 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。