MCPLow riskUnclaimed
Vigilis
Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.
piyushpathakqapiyushpathakqa/vigilis-mcp
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.piyushpathakqa/vigilis-mcp",
"description": "Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.",
"title": "Vigilis",
"repository": {
"url": "https://github.com/piyushpathakqa/Vigilis",
"source": "github"
},
"version": "0.4.1",
"websiteUrl": "https://vigilis.dev",
"packages": [
{
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"identifier": "vigilis-mcp",
"version": "0.4.1",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Pay-as-you-go Anthropic API key used to run the Vigilis agent (not a Claude.ai subscription).",
"isRequired": true,
"isSecret": true,
"name": "ANTHROPIC_API_KEY"
}
]
}
]
}Permissions
DeclaredDetected
Runs code—
nodeInstalls—
npm:vigilis-mcp@0.4.1Runs install scripts—None
NetworkNoneNone
Needs credentials
ANTHROPIC_API_KEYANTHROPIC_API_KEYOutside the workspace—None
Agent tools—None
Checks
Low risk · Nothing worth a warning was found.
Not reviewed by a person · Checked by rules; the model review is not switched on yet.
Versions
- #10.4.1latestOct 7, 2026
VigilisOpen in Codeg