Loading…
Credential isolation for AI agents. Inject secrets at the network boundary.
io.github.getaegis/aegis is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 70/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding io.github.getaegis/aegis to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
npx -y @getaegis/cli@1.0.5Review the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-08-06T09:04:18.03171Z",
"publishedAt": "2026-08-06T09:04:18.03171Z",
"statusChangedAt": "2026-08-06T09:04:18.03171Z"
}
},
"server": {
"name": "io.github.getaegis/aegis",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.0.5",
"packages": [
{
"version": "1.0.5",
"transport": {
"type": "stdio"
},
"identifier": "@getaegis/cli",
"registryType": "npm",
"environmentVariables": [
{
"name": "AEGIS_MASTER_KEY",
"format": "string",
"isSecret": true,
"isRequired": true,
"description": "Master encryption key for the credential vault"
},
{
"name": "AEGIS_SALT",
"format": "string",
"isSecret": true,
"isRequired": true,
"description": "Hex-encoded 32-byte salt for key derivation (generated by aegis init)"
},
{
"name": "AEGIS_DATA_DIR",
"format": "string",
"description": "Directory for vault databases and registry (default: .aegis/)"
},
{
"name": "AEGIS_PORT",
"format": "string",
"description": "Gate proxy port (default: 3100)"
},
{
"name": "AEGIS_LOG_LEVEL",
"format": "string",
"description": "Log verbosity: debug, info, warn, error (default: info)"
},
{
"name": "AEGIS_LOG_FORMAT",
"format": "string",
"description": "Log output format: json or pretty (default: json)"
},
{
"name": "AEGIS_VAULT",
"format": "string",
"description": "Named vault to use (default: default)"
},
{
"name": "AEGIS_REQUIRE_AGENT_AUTH",
"format": "string",
"description": "Require agent authentication on every request (true/false, default: false)"
},
{
"name": "AEGIS_POLICY_MODE",
"format": "string",
"description": "Policy enforcement mode: enforce, dry-run, or off (default: enforce)"
},
{
"name": "AEGIS_POLICIES_DIR",
"format": "string",
"description": "Directory containing YAML policy files"
},
{
"name": "AEGIS_METRICS",
"format": "string",
"description": "Enable Prometheus metrics endpoint (true/false, default: true)"
}
]
}
],
"repository": {
"url": "https://github.com/getaegis/aegis",
"source": "github"
},
"description": "Credential isolation for AI agents. Inject secrets at the network boundary."
}
}