Skip to content

Agents Shipgate

The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source…

Install

$uvx agents-shipgate fixture run ai_generated_refund_pr
Claude Code
claude mcp add agents-shipgate -- uvx agents-shipgate fixture run ai_generated_refund_pr
Cursor / Claude Desktop (mcp.json)
{
  "mcpServers": {
    "agents-shipgate": {
      "command": "uvx",
      "args": [
        "agents-shipgate",
        "fixture",
        "run",
        "ai_generated_refund_pr"
      ]
    }
  }
}

Install command taken from the project's README or registry entry. Always review code before running it.

Agents Shipgate

Your coding agent changed what your AI agent can do — Agents Shipgate shows you what changed before it merges.

The deterministic merge gate for AI-generated agent capability changes.

Local-first and static by default — no agent execution, tool calls, LLM calls, or network access.

Agents Shipgate is an open-source CLI and GitHub Action for local-first, static Tool-Use Readiness review. It scans MCP, OpenAPI, OpenAI Agents SDK, Anthropic Messages API, Google ADK, LangChain/LangGraph, CrewAI, OpenAI API, Codex repo config, Codex plugin, n8n, and Conductor OSS workflow artifacts, then writes a deterministic Tool-Use Readiness Report before your agent gets production-like permissions.

Application agent PRs without setup

The source build can compare OpenAI Agents SDK and Google ADK tool bindings without a manifest or baseline:

agents-shipgate diff --application --workspace /path/to/repo --base BASE_SHA --head HEAD_SHA

It shows source-observed changes per agent, including before/after signatures and source locations, in the package that holds the changed code's agents unless --scope names one. See application comparison for scoped applications, moves, exact refs and coverage limits. Version availability is recorded in the CHANGELOG entry: it is new in 1.2.0, the newest published release, so an older install needs pipx upgrade agents-shipgate first.

What did this PR change?

Start with a pull request you already have that changes what a coding agent may do: .claude/settings.json, .mcp.json, Codex, Cursor or VS Code MCP configuration. No manifest, policy, saved baseline, skill or account is needed, and nothing is written to your repository. From the PR branch, with its base branch available in your clone:

pipx install agents-shipgate
agents-shipgate diff

diff compares your working tree with its merge base on the repository's default branch (origin/HEAD, origin/main or origin/master) and prints one entry per changed grant or replaced rule. If the PR targets another branch, pass --base origin/<that-branch>; in a fork clone, fetch upstream and pass --base upstream/. On a PR that widens a Claude Code allow rule, drops a denial and adds an MCP server:

The example below is from this source tree, run in a clone, and is not yet released: the published 1.2.0 prints the same comparison, but its note on the added MCP server reads launch source is mutable. This tree states the declaration fact and the launch it leaves open apart (#933).

Agent capability diff  origin/main (5d1b9e23) -> working tree

⚠ high    added    claude-code .mcp.json
                  billing (command name npx; env keys BILLING_TOKEN)
                  an MCP tool surface the agent may call has changed; package spec has no exact version; launch resolution not established: npx may resolve a local project dependency or fall back to the registry/cache

⚠ medium  widened  claude-code .claude/settings.json
                  allow: Bash(npm test:*) → allow: Bash(npm *)
                  the new rule matches everything the old rule matched; runs without a prompt

⚠ low     removed  claude-code .claude/settings.json
                  deny: Bash(rm -rf:*) → gone
                  removes a denial the agent was subject to

Similar plugs

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io