
Aegis
io.github.getaegisPublished by GitHub account getaegisv1.0.5Updated Oct 24, 2026
Credential isolation for AI agents. Inject secrets at the network boundary.
Overview
A local-first credential isolation proxy that lets an AI assistant call external APIs through Aegis, which injects stored secrets at the network boundary.
- What you can do
- Make authenticated API calls to configured services, with Aegis injecting the stored credential instead of exposing it to the assistant (aegis_proxy_request). List the available service names, never the secrets themselves (aegis_list_services). Check Aegis status and health (aegis_health). Requests pass through the same pipeline as the HTTP gate: domain allowlists, agent authentication, body inspection, rate limiting and audit logging.
- When to use it
- Use it when an assistant needs to call services such as Slack, GitHub or Stripe but you do not want raw API keys in MCP config or reachable by the model, and you want domain restrictions and an audit trail on outbound calls.
- Requirements
- Runs locally over stdio as the npm package @getaegis/cli (Node.js 20 or newer). Requires initialization with aegis init and the secrets AEGIS_MASTER_KEY and AEGIS_SALT; credentials must be added to a vault first. Optional settings include AEGIS_DATA_DIR, AEGIS_POLICIES_DIR, AEGIS_POLICY_MODE, AEGIS_PORT, AEGIS_REQUIRE_AGENT_AUTH, AEGIS_VAULT, AEGIS_METRICS and log options. Network access to the target APIs is needed.
Installation
In SourceWeft
- Open Aegis in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Aegis
[CI] [npm version] [Docker] [License]
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
[How Aegis works — agent sends request through Gate, credentials injected at the network boundary]
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.com - No 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
Production Setup (with agent auth)
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):
After (Aegis — no key visible):
Generate the config for your AI host:
The MCP server exposes three tools:
The MCP server replicates the full Gate security pipeline: domain guard, agent auth, body inspection, rate limiting, audit logging.
Setup Guides
Features
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
See full comparison for detailed breakdowns against each approach.
Documentation
Install
Requires Node.js ≥ 20 — check with node -v
Development
See CONTRIBUTING.md for code style, PR process, and architecture overview.
License
Source: README.md at commit f1321b3
Tools
0Version history
1- v1.0.5LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts