AEGIS Governance
Provides governance decision tools via GitHub Action for automated proposal evaluation in CI/CD pipelines.
AEGIS Governance — MCP Server
Status: the hosted AEGIS service is offline (since September 2026). The hosted API and the hosted MCP endpoint (
mcp.aegis.undercurrentholdings.com) are offline. The local server does not evaluate proposals itself, so no tool returns an evaluation at this time. Current status: https://undercurrentholdings.com/status/
What the package is
aegis-governance on PyPI is a Python client for the AEGIS API. It also contains a local
MCP server. The package installs one console script, aegis-mcp-server. This script starts
a local MCP server that uses the stdio transport. The package has no other command-line tool.
The local server has no evaluation engine. By default, the client sends all requests to the hosted AEGIS API. Sandbox mode (the mode without an API key) also uses the hosted API. While the hosted service is offline, tool calls do not return evaluations.
Related MCP server: @vaibot/mcp-server
Install
pip install "aegis-governance[mcp]"The [mcp] extra is necessary for aegis-mcp-server. On Python < 3.10, the extra installs
nothing, and aegis-mcp-server exits with an install hint.
Local stdio MCP configuration
Claude Code
claude mcp add aegis -- aegis-mcp-serverCursor (.cursor/mcp.json) / Windsurf / any stdio MCP client:
{
"mcpServers": {
"aegis": { "command": "aegis-mcp-server" }
}
}VS Code (.vscode/mcp.json):
{
"servers": {
"aegis": { "type": "stdio", "command": "aegis-mcp-server" }
}
}Tools
tools/list from aegis-mcp-server in aegis-governance 1.4.2 returns these six tools.
Without AEGIS_API_KEY, aegis_evaluate_proposal and aegis_health call the hosted API, and
the other four tools return an AuthenticationError JSON result without an API call. With
AEGIS_API_KEY set, all six tools call the hosted API.
The descriptions below are quoted from the server. They do not describe a service that is available now.
Tool | Description (quoted from the server) |
| Evaluate an engineering proposal through the AEGIS gate checks. |
| Quick risk threshold check without a full Bayesian evaluation. |
| Check AEGIS API health (service status, version, components). |
| List recent governance decisions for the authenticated customer. |
| Fetch a specific governance decision by ID, with full gate detail. |
| Get the authenticated customer's evaluation usage report. |
Reading the source
The aegis-governance source repository is private. To read the published source, download
the source distribution (sdist) from PyPI:
pip download --no-binary :all: --no-deps "aegis-governance==1.4.2"Or get the .tar.gz file from the PyPI release files.
This server cannot be deployed
Maintenance
Related MCP Connectors
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
Related MCP Servers
- AlicenseBqualityCmaintenancePre-execution governance for AI agents. 45 MCP tools for hold queues, audit trails, risk scoring, and policy enforcement. Validates agent actions before they execute.4563 npm1MIT

@vaibot/mcp-serverofficial
FlicenseAqualityDmaintenanceGovernance circuit-breaker MCP server that enables AI agents to request risk-based decisions, approve or deny actions, and finalize outcomes with full audit receipts.4-- AlicenseAqualityAmaintenanceGovernance framework for LLM agents. Exposes seven mechanically-enforced rules plus tools for preflight file protection, audit-chain verification, session handoff and worklog templates, MCP config auditing, and an emergency kill switch.1236 npm4MIT
- AlicenseBqualityAmaintenanceA governance proxy for AI tools — every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.13MIT