Claude Code Multi-Process MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Claude Code 多进程 MCP 服务器
项目定位
基于 FastMCP 框架的多进程并行执行服务器,为 Claude Code CLI 提供异步任务处理能力。
Related MCP server: claude-code
核心架构
┌─────────────────────────────────────────────────────────────┐
│ Claude Code CLI │
└───────────────────────────┬─────────────────────────────────┘
│ JSON-RPC (stdio)
┌───────────────────────────▼─────────────────────────────────┐
│ FastMCP Server │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ @server.tool Decorators │ │
│ │ ┌─────────────┐ ┌──────────────┐ ┌──────────────┐ │ │
│ │ │execute_cc │ │start_cc_async│ │check_status │ │ │
│ │ │_task │ │ │ │ │ │ │
│ │ └─────────────┘ └──────────────┘ └──────────────┘ │ │
│ └─────────────────────────────────────────────────────┘ │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ TaskManager Class │ │
│ │ • SIGCHLD 信号处理 (自动回收僵尸进程) │ │
│ │ • 进程生命周期管理 │ │
│ │ • UUID 任务追踪 │ │
│ └─────────────────────────────────────────────────────┘ │
└───────────────────────────┬─────────────────────────────────┘
│ subprocess.Popen()
┌───────────────────────────▼─────────────────────────────────┐
│ 子进程池 (并行执行) │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ │
│ │ Task 1 │ │ Task 2 │ │ Task 3 │ │ Task N │ │
│ └─────────┘ └─────────┘ └─────────┘ └─────────┘ │
└─────────────────────────────────────────────────────────────┘
│
┌───────────────────────────▼─────────────────────────────────┐
│ 文件系统持久化 (/tmp/) │
│ • cc_process_tasks/ → 任务结果 (JSON) │
│ • *.stdout → 标准输出 │
│ • *.stderr → 错误输出 │
│ • cc_process_mcp.log → 运行日志 │
└─────────────────────────────────────────────────────────────┘MCP 工具集
工具名 | 类型 | 功能 |
| 同步 | 阻塞执行,返回结果 |
| 异步 | 立即返回 task_id |
| 查询 | 获取状态和结果 |
| 监控 | 列出所有运行中任务 |
| 清理 | 终止进程并删除数据 |
关键技术点
技术领域 | 实现方案 |
进程管理 |
|
僵尸进程防护 |
|
任务持久化 | 文件系统 JSON 存储 + 进程状态混合判断 |
进程存活检测 |
|
输出解析 | 支持 stream-json/json/text 多格式提取 |
任务隔离 | 每任务独立目录 + UUID 标识 |
技术栈
Python 3.6+ + FastMCP ≥0.12.0 + 标准库 (signal/subprocess/json)状态流转
启动 → running → (poll检测/文件mtime判断) → completed/failed/timeout
↑ ↓
└────────────── SIGCHLD 自动清理 ←────────────┘Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Let your AI sessions talk to each other — messaging, tasks, sessions, and alerts
Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.
Durable background job execution, async task scheduling, and state persistence for AI agents.
Stand up ops from Cursor/Claude/Codex; fleets keep running after your session ends.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables Claude Code to run OpenAI Codex (GPT-5) tasks asynchronously in the background, filtering out thinking logs to save 95% context tokens and allowing parallel execution.344MIT
- AlicenseNot gradedqualityDmaintenanceEnables Codex to delegate tasks to Claude Code, allowing Claude to investigate, edit, and verify changes in the repository with background job management.1 npmMIT
- AlicenseAqualityDmaintenanceEnables asynchronous and parallel execution of Gemini CLI tasks within Claude Code, allowing background task management and multi-instance parallelism.34MIT
- AlicenseAqualityDmaintenanceEnables Claude Code to spawn child sessions for parallel, asynchronous task execution, allowing users to continue working while tasks run in the background.3MIT