智能代理网关 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
确定性合并网关,用于AI生成的代理能力更改
智能代理网关 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
确定性合并网关,用于AI生成的代理能力更改
智能代理网关 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/ThreeMoonsLab/agents-shipgate
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"------": {
"command": "npx",
"args": ["-y", "agents-shipgate"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 智能代理网关 执行以下任务... Claude: [自动调用 智能代理网关 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"______": {
"command": "npx",
"args": ["-y", "agents-shipgate"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/readme-header-dark.png"> <img src="assets/readme-header.png" alt="Agents Shipgate · the deterministic merge gate for AI-generated agent capability changes" width="100%"> </picture> </p>
The core loop is verify-first: when a PR changes what your agent can do, run the deterministic verifier on the diff and read its merge verdict before you merge.
First ask whether Shipgate applies to the current repo or diff:
agents-shipgate verify --preview --json
If the repo is not configured yet, install the manifest, advisory CI, and agent-facing instructions:
agents-shipgate init --workspace . --write --ci --agent-instructions=default --json
Prefer to delegate? Paste the coding-agent snippet into Claude Code, Codex, or Cursor and let the agent wire the gate itself — the repo ships AGENTS.md managed blocks, llms.txt, and structured error output for exactly this path.
Then verify the committed PR/CI ref. Pass the base and head so the diff — the capability delta and trust-root signals — is in scope (the verifier never fetches; make the base ref available first, e.g. git fetch origin main):
agents-shipgate verify --workspace . --config shipgate.yaml \
--ci-mode advisory --format json --base origin/main --head HEAD
For local, uncommitted work, omit --base/--head so your working-tree edits are scanned instead:
agents-shipgate verify --workspace . --config shipgate.yaml \
--ci-mode advisory --format json
The release gate is agents-shipgate-reports/report.json → release_decision.decision (blocked | review_required | insufficient_evidence | passed). The PR/controller surface is agents-shipgate-reports/verifier.json → merge_verdict (`mergeable | human_review_required | insufficient_evidence | blocked | unknown`), a deterministic projection of the release decision. Read verifier.json first for merge_verdict, can_merge_without_human, first_next_action, fix_task, and capability_review.top_changes.
Zero-setup demos of both verdicts are in 60 seconds above; uvx runs them with no persistent install. To install the CLI, use pipx install agents-shipgate (then pipx upgrade agents-shipgate — a plain install is a no-op over a stale build). Your agent project does not need Python 3.12; the CLI installs separately. To verify your own repo and write the standard agents-shipgate-reports/ directory, see Verify your repo below.

Open a report first if you want to see the output shape before installing:
| Sample | Markdown | JSON |
|---|---|---|
support_refund_agent | [report.md](samples/support_refund_agent/expected/report.md) | [report.json](samples/support_refund_agent/expected/report.json) |
simple_openai_api_agent | [report.md](samples/simple_openai_api_agent/expected/report.md) | [report.json](samples/simple_openai_api_agent/expected/report.json) |
simple_langchain_agent | [report.md](samples/simple_langchain_agent/expected/report.md) | [report.json](samples/simple_langchain_agent/expected/report.json) |
The support_refund_agent fixture also includes a reviewer-shaped Release Evidence Packet in packet.md, packet.json, and packet.html.
The bundled support-refund fixture demonstrates the kind of release risks Agents Shipgate is designed to surface:
```text
高质量的MCP工具,适用于AI代理能力更改管理
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,智能代理网关 在MCP工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | agents-shipgate |
| 原始描述 | 开源MCP工具:The deterministic merge gate for AI-generated agent capability changes — a local。⭐27 · Python |
| Topics | ai-agentsmcpci-cd |
| GitHub | https://github.com/ThreeMoonsLab/agents-shipgate |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-06-17 · 更新时间:2026-06-17 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端