plimsoll
After a change, your agent asks plimsoll and gets a few findings back, each measured, each with its limit and a way to check it. Here is a real answer for the last 30 commits of Obtainium:
plimsoll 0.6.0 status: base `HEAD~30` e9087ce099, head 35c3e7fea4
3 new, 1 grown, 0 resolved; 14 more in `report` only
1. [new, exact] `pubspec.yaml` names 1 runtime dependency that was not there at the base: `cronet_http` (47 now, 46 at the base).
2. [new, candidate] `lib/pages/add_app.dart` `runSearch` crossed the limit of 25 in this change: cognitive complexity 22 → 46 (+24).
verify: read lines 388–627 (172 of them added by this change): it nests 7 levels deep at line 576; …
3. [grown, candidate] The ring of `lib/app_sources/apk4free.dart` has 77 files, 74 at the base.
verify: grown through `lib/components/app_list_tile.dart` line 9 importing `lib/app_sources/github.dart` and 20 more, added by this change; …
…What it catches
New dependencies a change slipped in, and whether a lockfile holds them.
Functions the change made hard to read: deep nesting or pasted blocks, in 11 languages.
Wiring: an import ring the change closed or grew, product code importing test code.
Process leftovers: a plan or review file committed, a setting defined twice or never read.
Related MCP server: CodeAudit MCP
Why you can trust it
Every finding is measured, names its limit and where that limit comes from, and says how to check it yourself. plimsoll only reads: no network, no telemetry, nothing written into your repository, nothing stored. Each mark was read blind on real agent pull requests before it was allowed into the short answer, and marks that failed that test show only in the full report. MIT licensed. It works next to your linters and CI, not instead of them. Guarantees and their tests.
Install
macOS and Linux, amd64 and arm64:
curl -fsSL https://raw.githubusercontent.com/julianzh0/plimsoll/main/install.sh | shThe script downloads the binary of the latest release, checks its
SHA-256 checksum and puts it in ~/.local/bin (PLIMSOLL_INSTALL_DIR changes the folder, PLIMSOLL_VERSION picks
a release). You can also download a binary and checksums.txt from the release page yourself, or build from source
with Go (see Development).
Windows, amd64 and arm64, in PowerShell:
irm https://raw.githubusercontent.com/julianzh0/plimsoll/main/install.ps1 | iexThe script does the same and puts plimsoll.exe in %LOCALAPPDATA%\plimsoll, which it adds to your user PATH
($env:PLIMSOLL_INSTALL_DIR and $env:PLIMSOLL_VERSION work as above). The Windows build is checked by compiling it,
not by a Windows test run.
plimsoll is listed in the official MCP registry as
io.github.julianzh0/plimsoll: clients that install from there get an MCP bundle with the binaries above.
Connect your agent
plimsoll is a local MCP server on standard input and output. It takes no argument and reads no setting.
Claude Code
claude mcp add plimsoll -- plimsollCodex (the CLI, the IDE extension and the ChatGPT desktop app share this setting)
codex mcp add plimsoll -- plimsollor in ~/.codex/config.toml:
[mcp_servers.plimsoll]
command = "plimsoll"OpenCode
opencode mcp add plimsoll -- plimsollAny other MCP client (Claude Desktop, Cursor, Antigravity and others), in its server configuration:
{
"mcpServers": {
"plimsoll": { "command": "plimsoll" }
}
}Then ask your agent, for example: "Use plimsoll to check what this branch did to the repository since main."
Tools
Tool | Returns |
| at most five new or grown marks, one line that counts the marks shown in |
| everything measured, in a fixed layout, the touched items included. Standing items of one kind past five are counted by folder in the text, and |
| the evidence of one mark, computed again and capped |
Without base, a question compares with the default base the repository declares in .plimsoll.toml, and the
answer's first line says so. Every result carries the text in content and the same answer as structuredContent. An answer may shorten, never
hide: what it leaves out it counts ("3 more: report lists them"), and report holds every mark.
Learn more
What plimsoll checks: every rule, what it measures and its limit, and your own limits, layout, ignored files and acknowledged items in
.plimsoll.toml.How each language is read: the eleven languages, how their imports and test code are found.
Guarantees and protocol: what plimsoll promises, with the tests that pin each promise.
Development: building, testing and the project's structure.
License
Available Tools
3 toolsexplainARead-only
Returns the evidence behind one mark, computed again: the files and patterns searched, the counts and what was left out.
Inputs: mark (required), repository (required), base. Returns: base, head, more, marks, +16 more
reportARead-only
Returns the full report of a repository against base: all marks, all measured numbers with their values at base, the standing debt item by item, the standing items the repository acknowledges, the footprint of the changes since base, and what was not analysed.
Inputs: repository (required), base, files. Returns: base, head, more, marks, +16 more
statusBRead-only
Returns what is new or has grown in a repository since base: at most five marks, each a measurement with its limit and a way to verify it, then one line each for what is listed in report only, for what the change touched but did not create and for added code without a use, one line of standing debt, one line that counts the standing items the repository acknowledges, the footprint of the changes since base, and what was not analysed.
Inputs: repository (required), base. Returns: base, head, more, marks, +16 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
explain (single-mark evidence drill-down), report (full repository report), and status (delta digest since base) each target a different granularity, and the descriptions make the distinction reasonably clear. The main risk is report vs status, since status returns a capped subset of what report already contains, which could cause an agent to pick the wrong one for a full picture.
All three names are single lowercase words in the same style: explain, report, status. There is no mixing of conventions or verb styles, so the naming is predictable even if it isn't a verb_noun pattern.
Three tools map cleanly onto three views (detail, full, delta) of the same analysis, so each earns its place. It is on the lean side for a measurement/reporting server, but not thin enough to be a mismatch.
The read surface is coherent (run a report, get a delta summary, verify a single mark), but there is no way to manage the baseline itself, list repositories, or acknowledge standing debt items even though report and status reference acknowledged items. These are notable gaps an agent would hit when trying to act on the findings rather than just read them.
Maintenance
Related MCP Connectors
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Repository knowledge graph MCP server for codebase understanding and debugging.
Permission-aware onboarding MCP server: answers about a codebase, filtered by the caller's role.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Related MCP Servers
- AlicenseBqualityDmaintenanceRead-only MCP server that exposes SonarQube Web API tools for issue retrieval, quality gate status, and source context, enabling coding agents to fix code issues.8203 npm1MIT
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server for AI coding agents to inspect repositories, audit code quality, route engineering skills, and plan safe issue/PR workflows.1MIT
- AlicenseAqualityCmaintenanceMCP server for git archaeology — churn hotspots, blame summaries, bus factor, commit forensics and file history over any local repository.113MIT
- FlicenseNot gradedqualityDmaintenanceLocal MCP server for static Python/TypeScript code audits, Playwright test generation, and SDLC health checks with a 0-100 quality score.-