agent-runner-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-runner-mcprun a command, read the exit protocol, and get an autopsy report"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
agent-runner-mcp
An MCP server that exposes the three-platform sandboxed runner protocol to any MCP client (Claude Code, Codex, and others): run tasks in an evidence-protected sandbox, read the EXIT protocol, and get an autopsy report. Zero dependencies — the MCP layer is hand-rolled. Every claim carries an experiment number.
一个把三平台沙箱 runner 协议暴露给任何 MCP 客户端(Claude Code、Codex 等)的 MCP server:在证据保护的沙箱里跑任务、读 EXIT 协议、拿尸检报告。零依赖——MCP 协议层手写。每个能力声明带实验编号。
为什么存在 / Why this exists
Agent 框架各自为政,但"在沙箱里可靠地执行任务并留下证据"是共性刚需。本 server 把 dsh-witness 的 runner 协议(lock=pid:startSec、EXIT:、尸检分类学)包装成 MCP 工具——Claude Code 实测 ✓ Connected,Codex 等 MCP 客户端同协议可接。
Related MCP server: Terminal MCP Server
工具 / Tools
工具 | 语义 |
| 沙箱执行命令(Windows ACL / Linux bwrap / macOS sandbox-exec 按平台自动选),返回任务目录 |
| 等终态(EXIT: 写入) |
| 按字节偏移增量读 out.log |
| 生成尸检报告(autopsy-spec 格式:manner/evidence/verdict/D-01~D-09) |
| 按 lock pid 击杀(崩溃实验) |
| 三证据收养判定(lock 解析 + 进程存活 + exit 协议) |
快速开始 / Quick start
# 安装(git 源)
dsh plugin --profile <name> add "github:Wang-Lin-Chang/agent-runner-mcp#v0.1.0"
# 注册到 Claude Code
claude mcp add agent-runner -- node dist/server.js
# 或直接跑测试(15 断言协议实测)
npm test验收证据 / Acceptance evidence
EXP-1:MCP 协议层实测 15/15(握手 / 六工具 / EXIT:0→D-01 / 崩溃→D-08 / EXIT:1→D-02)
EXP-2:Claude Code 2.1.92 真实客户端
✓ Connected(initialize + tools/list 握手)EXP-3:Windows ACL 持久性判决(观测产物与证据区分离)
EXP-4:死亡语义矩阵对齐 autopsy-spec 分类学
诚实边界 / Honest boundaries
Claude Code 会话内工具调用需登录态——本机未登录,协议握手实测、会话调用未实测不声称。
本 server 是 runner 协议层:完整 registry 级收养/事件溯源/缓存见 dsh-witness。
Windows CI 管理员环境下 ACL 沙箱失效 → runner fail-closed(EXIT:-998)为协议正确回应;沙箱能力验收在非管理员环境实测。
离线适用面:架构无网络依赖(本地进程 + 文件协议);数天级断网长跑未实测。
License
Apache-2.0
Maintenance
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
AlicenseAqualityFmaintenanceMCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.148MIT- Alicense-qualityCmaintenanceA production-ready MCP server for secure, session-based command execution, file manipulation, and system inspection via local terminal sessions.10ISC
- Flicense-qualityBmaintenanceAn MCP server exposing narrowly scoped storage workflows with Overseer approval integration and redacted execution evidence, currently in fixture-only development for testing via stdio.
- Alicense-qualityCmaintenanceA sandboxed MCP server that executes shell commands inside ephemeral, locked-down Docker containers with no network by default, dropped capabilities, and an audit log, enabling secure agent-driven command execution.15MIT
Related MCP Connectors
An MCP server for deep research or task groups
MCP protocol requiring task acceptance and provenance tags. Self-hosted only - see README.
ArcAgent MCP server for bounty discovery, workspace execution, and verified coding submissions.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Wang-Lin-Chang/agent-runner-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server