com.graneth/mcp-server
NPM · @GRANETH/MCP-SERVER · 2 COMPONENTS · SCANNED AUG 3
Pre-flight check for AI coding agents: hallucinated packages + hardcoded secrets. Free, no account.
Available components
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 →
Supply Chain Security86
- No malware found by supply-chain analysis.Pass
- Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.Partial
- No install/post-install scripts declared.Pass
- Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability62
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 452 tokens (~226/item across 2 items; 2 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 Management27
- Stability observed for 8 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
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
npm · @graneth/mcp-server
claude mcp add com-graneth-mcp-server -- npx -y @graneth/mcp-server
codex mcp add com-graneth-mcp-server -- npx -y @graneth/mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-graneth-mcp-server": {
"type": "local",
"command": [
"npx",
"-y",
"@graneth/mcp-server"
],
"enabled": true
}
}
} openclaw mcp add com-graneth-mcp-server --command npx --arg -y --arg @graneth/mcp-server
mcp_servers:
com-graneth-mcp-server:
command: "npx"
args: ["-y", "@graneth/mcp-server"] {
"mcpServers": {
"com-graneth-mcp-server": {
"command": "npx",
"args": [
"-y",
"@graneth/mcp-server"
]
}
}
} 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.
- 3 Aug 26 +4
- Stability: unverified → 0.27 ▲ functional
- 2 Aug 26 +42
- Provenance: unverified → fail ▼ security
- Known CVEs: unverified → partial ▲ security
- Install scripts: unverified → pass ▲ security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Dependency health: unverified → partial ▲ functional
- License: unverified → pass ▲ functional
- Maintenance: unverified → pass ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Licence: MIT functional
- 1 Aug 26 −12
- Malware scan: unverified → pass ▲ security
- Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- 31 Jul 26 +9
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 30 Jul 26 −52
- Install scripts: pass → unverified ▼ security
- Known CVEs: partial → unverified ▼ security
- Provenance: fail → unverified ▼ security
- Dependency health: partial → unverified ▼ functional
- Maintenance: pass → unverified ▼ functional
- License: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- Licence: MIT functional
- 27 Jul 26 +38
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Jul 26 32
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 3 Aug 2026 · Analysed npm/@graneth/[email protected]
Provenance none
Ecosystem: npm · Outcome: none
Dependencies 94 packages
94 packages in the resolved dependency tree · 94 deprecated · 29 stale.
The dependency tree was only partially resolved, so these counts may be incomplete.
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.
pre_flight_check ~242
Security pre-flight check for local file changes BEFORE committing. Run this whenever you are about to suggest `git commit`, `git push`, or open a pull request — especially when changes add package imports or dependencies (package.json / requirements.txt / Cargo.toml / go.mod / Gemfile / composer.json / import statements) or could contain secrets. Detects AI-hallucinated (non-existent) packages by live-checking six registries (npm, PyPI, crates.io, RubyGems, Go module proxy, Packagist) plus a bundled public threat-feed snapshot, which keeps catching a known hallucinated name even after an attacker registers it; risk-scores dependencies an AI agent introduced by compounding metadata signals (new + install-scripts + low-adoption + no-provenance = an attack shape no single check flags); and finds hardcoded credentials via pattern + entropy analysis. Always free, no account required. Returns CLEAR, REVIEW_REQUIRED, or BLOCKED with specific findings and remediation.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | — | What these changes do (helps triage) |
| files | array | yes | Files staged for commit (path + content) |
No output schema declared.
No examples provided.
report_hallucination ~210
Report an AI-hallucinated package name to Graneth's public threat feed, so every user's pre-flight catches it — permanently, even if an attacker registers the name later. IMPORTANT: only call this AFTER the human has explicitly agreed to report the name; ask them first. Sends exactly one package name + ecosystem to graneth.com (never file contents). The server re-verifies non-existence against the live registry before accepting. Reportable ecosystems: npm (unscoped), pypi, crates, gems — namespaced names (npm @scope, go, composer) are rejected to keep internal package names out of a public feed. Optional `reporter` is a public attribution handle shown on the feed entry.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | yes | Registry the name was checked against |
| package | string | yes | The hallucinated package name (as caught by pre_flight_check) |
| reporter | string | — | Optional public attribution handle ([a-zA-Z0-9_-]) |
No output schema declared.
No examples provided.