Aegis
Aegis is a local-first credential isolation proxy that allows AI agents to make authenticated API calls without ever seeing, storing, or transmitting real credentials. It injects secrets at the network boundary and enforces security policies.
Make authenticated API calls (
aegis_proxy_request): Send HTTP requests (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) to registered services (e.g., Slack, GitHub, Stripe) by specifying a service name and API path — Aegis automatically injects credentials without exposing them. Supports custom headers, request bodies, and optional host overrides (within the credential's allowed domain list).List available services (
aegis_list_services): Retrieve all registered services, including their names, authentication types, and allowed domains — without revealing actual secrets.Check server health (
aegis_health): Verify the proxy is running and healthy, including counts of registered credentials and agents.Enforce security policies: Domain restrictions prevent unauthorized data exfiltration, and body inspection blocks credential patterns from leaking through requests.
Maintain audit trails: All requests — both allowed and blocked — are logged with full context for security monitoring.
Integrate natively with MCP-compatible AI agents like Claude, Cursor, VS Code, Windsurf, and Cline.
Enables AI agents to make authenticated calls to GitHub APIs via a local proxy that handles credential injection and enforces domain-restricted access policies.
Provides a secure proxy for AI agents to interact with Slack APIs, injecting bot tokens at the network boundary to ensure agents never see the raw credentials.
Facilitates secure interaction with Stripe APIs by injecting API keys at the proxy level, allowing AI agents to perform operations while maintaining credential isolation.
Aegis
Stop putting API keys where AI agents can read them.
Aegis is a local-first credential isolation proxy for AI agents. It sits between your agent and the APIs it calls — injecting secrets at the network boundary so the agent never sees, stores, or transmits real credentials.
How It Works
Related MCP server: agent-auth
Why?
AI agents (Claude, GPT, Cursor, custom bots) increasingly call real APIs — Slack, GitHub, Stripe, databases. The current pattern is dangerous:
Agents see raw API keys — one prompt injection exfiltrates them
No domain guard — a compromised agent can send your Slack token to
evil.comNo audit trail — you can't see what an agent did with your credentials
No access control — every agent can use every credential
Aegis solves all four. Your agent makes HTTP calls through a local proxy. Aegis handles authentication, enforces domain restrictions, and logs everything.
Quick Start
# Install
npm install -g @getaegis/cli
# Initialize (stores master key in OS keychain by default)
aegis init
# Add a credential
aegis vault add \
--name slack-bot \
--service slack \
--secret "xoxb-your-token-here" \
--domains slack.com
# Start the proxy
aegis gate --no-agent-auth
# Test it — Aegis injects the token, forwards to Slack, logs the request
# X-Target-Host tells Gate which upstream server to forward to (optional if credential has one domain)
curl http://localhost:3100/slack/api/auth.test \
-H "X-Target-Host: slack.com"Production Setup (with agent auth)
# Create an agent identity
aegis agent add --name "my-agent"
# Save the printed token — it's shown once only
# Grant it access to specific credentials
aegis agent grant --agent "my-agent" --credential "slack-bot"
# Start Gate (agent auth is on by default)
aegis gate
# Agent must include its token
curl http://localhost:3100/slack/api/auth.test \
-H "X-Target-Host: slack.com" \
-H "X-Aegis-Agent: aegis_a1b2c3d4..."MCP Integration
Aegis is a first-class MCP server. Any MCP-compatible AI agent can use it natively — no HTTP calls needed.
Before (plaintext key in config):
{
"mcpServers": {
"slack": {
"command": "node",
"args": ["slack-mcp-server"],
"env": { "SLACK_TOKEN": "xoxb-1234-real-token-here" }
}
}
}After (Aegis — no key visible):
{
"mcpServers": {
"aegis": {
"command": "npx",
"args": ["-y", "@getaegis/cli", "mcp", "serve"]
}
}
}Generate the config for your AI host:
aegis mcp config claude # Claude Desktop
aegis mcp config cursor # Cursor
aegis mcp config vscode # VS Code
aegis mcp config cline # Cline
aegis mcp config windsurf # WindsurfThe MCP server exposes three tools:
Tool | Description |
| Make an authenticated API call (provide service + path, Aegis injects credentials) |
| List available services (names only, never secrets) |
| Check Aegis status |
The MCP server replicates the full Gate security pipeline: domain guard, agent auth, body inspection, rate limiting, audit logging.
Setup Guides
Features
Feature | Description |
Encrypted Vault | AES-256-GCM encrypted credential storage with PBKDF2 key derivation |
HTTP Proxy (Gate) | Transparent credential injection — agent hits |
Domain Guard | Every outbound request checked against credential allowlists. No bypass |
Audit Ledger | Every request (allowed and blocked) logged with full context |
Agent Identity | Per-agent tokens, credential scoping, and rate limits |
Policy Engine | Declarative YAML policies — method, path, rate-limit, time-of-day restrictions |
Body Inspector | Outbound request bodies scanned for credential-like patterns |
MCP Server | Native Model Context Protocol for Claude, Cursor, VS Code, Windsurf, Cline |
Web Dashboard | Real-time monitoring UI with WebSocket live feed |
Prometheus Metrics |
|
Webhook Alerts | HMAC-signed notifications for blocked requests, expiring credentials |
RBAC | Admin, operator, viewer roles with 16 granular permissions |
Multi-Vault | Separate vaults for dev/staging/prod with isolated encryption keys |
Shamir's Secret Sharing | M-of-N key splitting for team master key management |
Cross-Platform Key Storage | OS keychain by default (macOS, Windows, Linux) with file fallback |
TLS Support | Optional HTTPS on Gate with cert/key configuration |
Configuration File |
|
Example Integrations
Step-by-step guides with config files and policies included:
Slack Bot — Protect your Slack bot token with domain-restricted proxy access
GitHub Integration — Secure GitHub PAT with per-agent grants and read-only policies
Stripe Backend — Isolate Stripe API keys with body inspection and rate limiting
OpenClaw Skill — Aegis skill for OpenClaw personal AI assistant
Security
Published STRIDE threat model — 28 threats analysed, 0 critical/high unmitigated findings
Full security architecture documentation (trust boundaries, crypto pipeline, data flow)
AES-256-GCM + ChaCha20-Poly1305 encryption at rest
Domain guard enforced on every request — no bypass
Agent tokens stored as SHA-256 hashes — cannot be recovered, only regenerated
Request body inspection for credential pattern detection
Open source (Apache 2.0) — read the code
How Aegis Compares
| Vault/Doppler | Infisical | Aegis | |
Agent sees raw key | Yes | Yes (after fetch) | Yes (after fetch) | No — never |
Domain restrictions | No | No | No | Yes |
MCP-native | No | No | Adding | Yes |
Local-first | Yes | No | No | Yes |
Setup | 10 sec | 30+ min | 15+ min | ~2 min |
See full comparison for detailed breakdowns against each approach.
Documentation
Document | Description |
Full reference: CLI commands, configuration, RBAC, policies, webhooks, troubleshooting | |
Trust boundaries, crypto pipeline, data flow diagrams | |
STRIDE analysis — 28 threats, mitigations, residual risks | |
Detailed comparison with .env, Vault, Doppler, Infisical | |
Common questions and objections | |
Feature roadmap | |
Code style, PR process, architecture overview |
Install
# npm
npm install -g @getaegis/cli
# Homebrew
brew tap getaegis/aegis && brew install aegis
# Docker
docker run ghcr.io/getaegis/aegis --helpRequires Node.js ≥ 20 — check with node -v
Development
git clone https://github.com/getaegis/aegis.git
cd aegis
yarn install
yarn build
yarn testSee CONTRIBUTING.md for code style, PR process, and architecture overview.
License
Available Tools
3 toolsaegis_healthAegis Health CheckB
Check the health status of Aegis, including credential and agent counts.
Inputs: no named parameters.
aegis_list_servicesAegis List ServicesA
List all available services registered in Aegis. Returns service names, auth types, and allowed domains — never secrets.
Inputs: no named parameters.
aegis_proxy_requestAegis Proxy RequestB
Make an authenticated API call through Aegis. Credentials are injected automatically — you never see them. Provide the service name and API path; Aegis handles authentication.
Inputs: path (required), service (required), body, method, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: health monitoring, service listing, and proxying requests. There is no overlap in functionality, and an agent can easily differentiate between them based on their specific roles.
All tool names follow a consistent 'aegis_' prefix with descriptive snake_case suffixes (health, list_services, proxy_request). This pattern is uniform across all tools, making them predictable and easy to understand.
With only 3 tools, the server feels minimal for a service management system like Aegis. While the tools cover basic operations, the scope might be too thin, potentially lacking advanced management features like service registration or configuration updates.
The tools provide core functionality for health checks, service listing, and proxying requests, but there are notable gaps. For example, there are no tools for managing services (e.g., adding or removing services) or handling authentication configurations, which could limit agent workflows in a service management context.
Maintenance
Related MCP Connectors
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Give your AI hands. Identity, credential vault, and API gateway for autonomous agents.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceSelf-hosted credential store and API proxy for AI agents. One Bearer token, all your services. Handles OAuth refresh, encrypted storage, audit logging, and per-agent permissioning.79 npm1MIT
- AlicenseNot gradedqualityDmaintenanceZero-knowledge credential injection for AI agents. Your agent authenticates to websites and APIs without ever seeing a password, TOTP code, or API key.15 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to securely access authenticated services (HTTP, SSH, SMTP) without exposing secrets, by acting as a server-side proxy that injects authentication.MIT
- AlicenseNot gradedqualityBmaintenanceBounded egress gateway & secret proxy for AI agents and applications, enabling safe credential injection into upstream requests while keeping raw secrets out of LLM prompt contexts.24 npmMIT