mergetrainSAFE
Local merge queue for parallel LLM agents in Git worktrees. Test combined code changes, require approval for Git pushes, and recover interrupted pushes.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/yongjip/mergetrain/actions/workflows/ci.yml) [](https://pypi.org/project/mergetrain/) [](https://pypi.org/project/mergetrain/) [](https://github.com/yongjip/mergetrain/blob/main/LICENSE)
Safely integrate committed branches from parallel coding agents.
mergetrain integrates committed branches from coding-agent Git worktrees on your machine. A train is a group of queued task branches. A gate is a configured test or check. Each agent commits and enqueues its branch. One runner merges branches in enqueue order and runs gates on the combined result. It updates your Git refs atomically only after explicit approval.
mergetrain is designed for one operator managing local repositories.
There is no mergetrain account, hosted control plane, OAuth app, or product telemetry. Queue and runner state stay on your machine. Only your configured Git remote and trusted gate or verification commands may contact external services.
The problem
Worktrees let several agents edit one repository without sharing a checkout. They do not decide landing order, test the combined result, prevent push races, or tell you what happened if a laptop dies mid-push.
Without a shared integration workflow, the operator chooses branch order and resolves cross-branch failures. The operator also reruns tests and controls pushes. Repeating these actions can slow parallel work.
<img src="https://raw.githubusercontent.com/yongjip/mergetrain/main/docs/images/mergetrain-explainer.gif" alt="Three coding agents enqueue branches. One runner assembles and tests their combined train before one atomic push." width="720">
mergetrain r
75323d1e9c83OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mergetrain -- uvx mergetrain==3.4.1 mcp
Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (11)
secret = "fixture-secret-output"
.mergetrain.yaml
exec(_fixed_slug_source(), namespace)
os.environ.copy() ... urllib.request
url = f"http://127.0.0.1:{server.server_address[1]}/hook""gnp.txe",
self.assertEqual(escape_controls("ab
"), "\\u202eab\\u2028")- The Codex sandbox may be unable to read `gh` credentials from the macOS
The sandbox may not read credentials stored in the macOS Keychain. Before
boundary. A coding agent with general shell access and a credential accepted by
Gates applied: no_behavioural_pass.
75323d1e9c83full audit observations/trust-audit/mcp-server/yongjip__mergetrain.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 75323d1e9c83 | SAFE | B | 88 | first audit |
Questions
What is the mergetrain MCP server?
Local merge queue for parallel LLM agents in Git worktrees. Test combined code changes, require approval for Git pushes, and recover interrupted pushes.
Is mergetrain safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does mergetrain need?
It reads FIXTURE_EVENT_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does mergetrain run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mergetrain.
How current is this page?
The grade is for one exact copy of the source (75323d1e9c83), read on 2026-10-11. The repository is watched and re-audited when it changes.