Mergetrain
PYPI · MERGETRAIN
Queue parallel-agent worktree branches, test together, serialize and recover Git pushes.
Available components
Last scanned (10 hours ago)
Scores higher than 95% of PyPI servers
Category CI/CD and DevOps
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 0 of 1 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to yongjip/mergetrain). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 9 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 839 tokens (~167/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 42% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 29 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 27 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 26 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Stability: 0.97 → pass security
- Package version: 3.7.0 → 3.7.1 functional
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Oct 26 +15
- Malware scan: unverified → pass ▲ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/mergetrain@3.7.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | yongjip/mergetrain |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/yongjip/mergetrain/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 3490955255 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:ac8b46976bdd004fc116b7678e8706a4476e56d60625296b1b9624db6c10e5cc |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 1 package
| Packages resolved | 1 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
mergetrain_deploy ~87
Deploy one exact validated plan after client-rendered human confirmation.
| Name | Type | Req | Description |
|---|---|---|---|
| repo | string | – | Filesystem path of the mergetrain project root to operate on. Defaults to the repository this server was launched in. Must be a checkout already configured by `mergetrain init`; any other path is ref… |
Structured output declared, but exposes no named fields.
No examples provided.
mergetrain_enqueue ~141
Queue a committed branch, pinning the SHA that was reviewed. The CLI always captures the exact clean commit, so later work on the branch cannot ride along silently. ``--auto`` is not a parameter -- unattended deploy is not reachable from here.
| Name | Type | Req | Description |
|---|---|---|---|
| branch | string | yes | – |
| repo | string | – | Filesystem path of the mergetrain project root to operate on. Defaults to the repository this server was launched in. Must be a checkout already configured by `mergetrain init`; any other path is ref… |
| task | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
mergetrain_inspect ~119
Inspect one job; request bounded events or raw log text explicitly.
| Name | Type | Req | Description |
|---|---|---|---|
| after_event_id | integer | – | – |
| detail | string | – | – |
| job_id | integer | yes | – |
| limit | integer | – | – |
| repo | string | – | Filesystem path of the mergetrain project root to operate on. Defaults to the repository this server was launched in. Must be a checkout already configured by `mergetrain init`; any other path is ref… |
Structured output declared, but exposes no named fields.
No examples provided.
mergetrain_status ~135
Current queue state, action-required work, and the exact next action. The payload's ``repo`` field names the checkout that answered. Linked worktrees may share its queue; read health and next_action before treating the state as ready for handoff.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| repo | string | – | Filesystem path of the mergetrain project root to operate on. Defaults to the repository this server was launched in. Must be a checkout already configured by `mergetrain init`; any other path is ref… |
Structured output declared, but exposes no named fields.
No examples provided.
mergetrain_validate ~160
Validate the queued train without pushing anything. Run it only when the user explicitly asked for validation or for the complete validation-and-deployment workflow; asking to queue work for validation authorizes enqueue only. Not read-only either: it creates a worktree, runs the configured gate commands, and moves jobs to ``validated`` or ``blocked``. The annotations say so rather than claiming otherwise to the client.
| Name | Type | Req | Description |
|---|---|---|---|
| repo | string | – | Filesystem path of the mergetrain project root to operate on. Defaults to the repository this server was launched in. Must be a checkout already configured by `mergetrain init`; any other path is ref… |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the Mergetrain MCP server?
Mergetrain runs locally as a PyPI package, launched with uvx mergetrain mcp. The registry lists launch arguments for this package that we cannot show safely, so they are left out. Check the registry entry for what the server needs. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mergetrain
claude mcp add yongjip-mergetrain -- uvx mergetrain mcp
The registry lists launch arguments for this package that we cannot show safely, so they are left out. Check the registry entry for what the server needs.
What is the Mergetrain MCP server?
Mergetrain is an MCP server listed in the public MCP registry as io.github.yongjip/mergetrain. Queue parallel-agent worktree branches, test together, serialize and recover Git pushes. This page covers its PyPI package (mergetrain).
Is the Mergetrain MCP server safe to use?
Mergetrain scores 92 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Mergetrain MCP server expose?
Mergetrain exposes 5 tools: mergetrain_status, mergetrain_inspect, mergetrain_validate, mergetrain_enqueue, mergetrain_deploy. Their descriptions and schemas cost roughly 642 tokens of context every time the server is loaded.
Is the Mergetrain MCP server still maintained?
Mergetrain is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Mergetrain MCP server under?
Mergetrain declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Mergetrain MCP server?
VerifyMCP ran 16 checks on Mergetrain, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.