Groundrule
NPM · @GROUNDRULE/CLI
Your repository's engineering standards for coding agents: rules per file, CI check, rule proposals.
Available components
Last scanned (6 hours ago)
Scores higher than 72% of npm servers
Category Developer Tools
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 Security95
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known medium-severity CVE affects glob 13.0.6, reached via @groundrule/core > sigstore > @sigstore/sign > make-fetch-happen > cacache > glob. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 6 of 62 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Metricall-AI-Lab/groundrule-oss). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 5 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 685 tokens (~171/item across 4 items; 4 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 Management23
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 −1
- CVE-2026-118764 affects this package: medium ▼ security
- CVE-2026-118773 affects this package: medium ▼ security
- Known CVEs: pass → fail ▼ security
- 29 Oct 26 81
First indexed and scored.
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 npm/@groundrule/cli@0.23.1
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 | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Metricall-AI-Lab/groundrule-oss |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Metricall-AI-Lab/groundrule-oss/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 3567260586 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:3d004dfa33bff04167ab8b63e3a8747508ec1a5805e13f788db09c8ab817c8c11418f19a4bdf2d6237ed55d82f88ca223eca35ad5ec4e73ec9db6114f |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 2 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-3g3m-2fjr-6pw4 | CVE-2026-118773 | medium | yes | |
| GHSA-g3hv-75wg-m249 | CVE-2026-118764 | medium | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 62 packages
| Packages resolved | 62 |
|---|---|
| Stale | 6 |
| 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 →
check Check changes against the standards ~148
Run the team's Groundrule checks on your changes, the same checks CI runs. By default it checks uncommitted changes (staged, unstaged and new files). Call it before you finish a change and fix every blocking finding; warnings don't fail the check, but fix the ones in code you wrote. Only findings the change introduced are reported. In a repository connected to its workspace, the counts per rule go to the workspace (never paths, lines or code).
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | Check every file, not only changes. Slower; reports existing problems too. |
| base | string | – | Check everything changed since this git ref instead, e.g. origin/main for a whole branch. |
No output schema declared.
No examples provided.
list_standards List engineering standards ~95
List the engineering standards in effect in this repository: ID, title, severity, rollout stage for organization rules, and what each requires. Follow every rule listed; at advise, checks report findings as warnings, and at enforce they fail at the rule's severity. Also use it to check whether a rule already exists before proposing one.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | – | Only standards whose ID, title, or requirement contain these words. |
No output schema declared.
No examples provided.
propose_rule Propose a rule to the team ~209
Propose an engineering rule for this team's Groundrule rulebook, for reviewers to accept or reject. Use it when the developer corrects how code here should be written and says, or confirms when you ask, that it should apply to everyone from now on (for example: "we never call Stripe directly, use PaymentsGateway"). Do not use it for one-off preferences, for rules list_standards already shows, or without the developer's agreement. Write the rule as one clear sentence. Tell the developer you proposed it and that a reviewer decides.
| Name | Type | Req | Description |
|---|---|---|---|
| example | string | – | A short code example of the right or wrong way, if helpful. |
| file | string | – | Repository-relative path where it came up, if any. |
| line | integer | – | Line in that file, if any. |
| rule | string | yes | The rule, as one clear sentence: what to do or never do. |
| why | string | – | Why, in the developer's words, if they said. |
No output schema declared.
No examples provided.
rules_for Rules for the files you're about to change ~89
The engineering standards that name the given files (by path or language), blocking first, each with what it requires and how to comply. Call it with the repository-relative paths you are about to create or edit, before editing. Rules that apply everywhere are not repeated here; they are in the agent file.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | yes | Repository-relative paths, e.g. src/payments/refund.ts. |
No output schema declared.
No examples provided.
How do I install the Groundrule MCP server?
Groundrule runs locally as an npm package, launched with npx -y @groundrule/cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @groundrule/cli
claude mcp add metricall-ai-lab-groundrule -- npx -y @groundrule/cli
What is the Groundrule MCP server?
Groundrule is an MCP server listed in the public MCP registry as io.github.Metricall-AI-Lab/groundrule. Your repository's engineering standards for coding agents: rules per file, CI check, rule proposals. This page covers its npm package (@groundrule/cli).
Is the Groundrule MCP server safe to use?
Groundrule scores 82 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 5 November 2026. It declares no install or post-install scripts. 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 Groundrule MCP server expose?
Groundrule exposes 4 tools: list_standards, rules_for, check, propose_rule. Their descriptions and schemas cost roughly 541 tokens of context every time the server is loaded.
Is the Groundrule MCP server still maintained?
Groundrule 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 Groundrule MCP server under?
Groundrule declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.