
Aegis
io.github.getaegis由 GitHub 帳號 getaegis 發布v1.0.5更新於 Oct 24, 2026
Credential isolation for AI agents. Inject secrets at the network boundary.
概覽
本地優先的憑證隔離代理,讓 AI 助理透過 Aegis 呼叫外部 API,由它在網路邊界注入已儲存的密鑰。
- 可以做什麼
- 向已設定的服務發出帶驗證的 API 呼叫,由 Aegis 注入儲存的憑證,助理本身看不到密鑰(aegis_proxy_request)。列出可用服務名稱,絕不回傳密鑰內容(aegis_list_services)。查詢 Aegis 的運作狀態與健康狀況(aegis_health)。請求與 HTTP 閘道走同一套流程:網域白名單、代理身分驗證、請求內容檢查、限流與稽核日誌。
- 適用情境
- 當助理需要呼叫 Slack、GitHub、Stripe 等服務,但你不希望把原始 API 密鑰寫進 MCP 設定或讓模型看到,並希望對外送請求做網域限制與稽核時使用。
- 執行需求
- 以 npm 套件 @getaegis/cli 在本機透過 stdio 執行,需要 Node.js 20 或更新版本。需先執行 aegis init 初始化,並提供密鑰 AEGIS_MASTER_KEY 與 AEGIS_SALT;憑證須先加入 vault。選用設定包括 AEGIS_DATA_DIR、AEGIS_POLICIES_DIR、AEGIS_POLICY_MODE、AEGIS_PORT、AEGIS_REQUIRE_AGENT_AUTH、AEGIS_VAULT、AEGIS_METRICS 及日誌選項。需要連線至目標 API 的網路。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Aegis,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
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
來源:README.md,提交 f1321b3
工具
0版本歷史
1- v1.0.5最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分