Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Aegis MCP Serversummarize my current role and access permissions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
aegis-mcp-server
MCP enforcement layer for the Aegis agent governance specification.
The spec writes the law. The CLI generates the law. This enforces the law.
What It Does
aegis-mcp-server is an MCP server that validates every agent action against your .agentpolicy/ files before it happens. Path permissions, content scanning, role boundaries, quality gates — all enforced at runtime with zero token overhead to the agent.
The agent never loads your governance files. The MCP server reads them into its own process memory and validates silently. The agent calls governed tools (aegis_write_file, aegis_read_file, etc.) and gets back either a success or a blocked response with the specific reason.
Quick Start
npm install -g aegis-mcp-server
# Or use npx
npx aegis-mcp-server --project . --role defaultClaude Code Configuration
{
"mcpServers": {
"aegis": {
"command": "npx",
"args": ["aegis-mcp-server", "--project", ".", "--role", "default"]
}
}
}For role-specific enforcement:
{
"mcpServers": {
"aegis": {
"command": "npx",
"args": ["aegis-mcp-server", "--project", ".", "--role", "backend"]
}
}
}Tools
Tool | What it does | Token cost |
| Pre-check if an operation is allowed | Tiny — just the verdict |
| Write with path + content validation | Same as a normal write |
| Read with path validation | Same as a normal read |
| Delete with path validation | Tiny — just the verdict |
| Execute a command in project root | Command output only |
| Run quality gates before marking done | Gate results only |
| Minimal role + permissions summary | ~200 tokens |
Zero Token Overhead
Traditional approach: load governance files into the agent's context window. Token cost scales with policy complexity.
Aegis MCP approach: the server loads policy into its own process memory. The agent calls tools and gets structured results. A project with 200 lines of governance has the same token cost as one with 20 lines. The complexity is absorbed by the server, not the agent.
Enforcement
Governance boundaries —
writable,read_only,forbiddenpath lists from governance.jsonRole scoping — agents confined to their role's writable and readable paths
Sensitive pattern detection — content scanned against governance-defined patterns
Cross-domain boundaries — imports validated against shared interface rules (when configured)
Quality gate validation —
pre_commitflags mapped tobuild_commandsand executedOverride logging — violations logged to append-only
overrides.jsonlImmutable policies — designated rules that cannot be overridden, even with human confirmation
Architecture
Agent ──→ aegis-mcp-server ──→ File System
│
├── Loads .agentpolicy/ into process memory (once)
├── Watches for policy changes (auto-reload)
├── Validates every tool call against policy
└── Returns success or blocked with reasonThree artifacts, one governance framework:
aegis-spec — Writes the law
aegis-cli — Generates the law
aegis-mcp-server — Enforces the law
License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.