s-gw MCP server
A local stdio MCP server that enables coding agents to discover credential handles and create scoped action requests with local approval and sanitized output.
README
<p align="center"> <img src="assets/icons/s-gw-128.png" alt="s-gw" width="96" height="96"> </p>
<h1 align="center">s-gw</h1>
<p align="center"> <strong>Local credential control for coding agents.</strong><br> Approve bounded actions locally. Keep raw credentials out of model context and tool output. </p>
<p align="center"> <a href="https://github.com/sgateway/s-gw/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/sgateway/s-gw/actions/workflows/ci.yml/badge.svg"></a> <a href="https://www.npmjs.com/package/@s-gw/s-gw"><img alt="npm" src="https://img.shields.io/npm/v/%40s-gw%2Fs-gw"></a> <a href="LICENSE"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/license-Apache--2.0-2ea44f"></a> <img alt="Node.js 20+" src="https://img.shields.io/badge/Node.js-20%2B-43853d"> <a href="https://s-gw.com"><img alt="Website: s-gw.com" src="https://img.shields.io/badge/website-s--gw.com-22c55e"></a> <img alt="Project status: preview" src="https://img.shields.io/badge/status-preview-f59e0b"> </p>
<p align="center"> <a href="https://s-gw.com">Demo</a> · <a href="#quick-start">Quick start</a> · <a href="docs/README.md">Documentation</a> · <a href="SECURITY.md">Security</a> · <a href="CONTRIBUTING.md">Contributing</a> </p>
s-gw is a local gateway between coding agents and credentials. Agents work with typed handles and scoped action requests. You approve the request on your machine, s-gw resolves the credential inside a constrained local process, and the agent gets sanitized output instead of the raw value.
[!IMPORTANT] s-gw is an early preview. Storage formats and interfaces may change, Windows support is still experimental, and the project has not completed an independent security audit. Do not treat it as a replacement for endpoint security or a hardened enterprise secrets platform yet.
What It Does
| Govern | Approve | Execute | Audit |
|---|---|---|---|
| Turn secrets into typed local handles that agents can reference safely. | Review the requesting agent, handle, command, environment binding, working directory, and target before access is granted. | Inject the credential only into the approved child process on the same machine. | Record request, approval, execution, policy, and destination evidence without storing returned raw secrets. |
Why Teams Use It
- Local custody: raw values stay in macOS Keychain, Windows Credential Manager, 1Password, or the encrypted local ledger.
- Action-scoped access: grants bind to the agent, handle, command, environment variable, working directory, target, approval mode, and optional time window.
- Useful handles: agents can request real work with stable handle names instead of seeing keys, passwords, tokens, or SSH material.
- Output sanitization: command output is scanned before it returns to the agent, replacing detected credential values with handles.
- Agent-aware setup: Codex, Claude Code, Cursor, OpenCode, Gemini CLI, GitHub Copilot, VS Code, and other MCP clients get profile-specific configuration.
- Local operator UI: the macOS app, menu helper, CLI, and web console show approvals, credential inventory, policies, usage flow, activity, and audit history.
Demo
Public demo: s-gw.com. The demo highlights the local console, trust loop, approval flow, supported agent catalog, and usage map.

How It Works
flowchart LR
A["Coding agent"] -->|"Handle + action request"| G["s-gw local gateway"]
G --> U["Local approval"]
U --> R["Constrained runner"]
K[("Keychain / Credential Manager / encrypted store")] --> R
R -->|"Sanitized output"| G
G --> A
The agent never needs the unlock passphrase or raw credential. Approval is scoped to the requested operation rather than granting general access to the store.
Core Surfaces
| Surface | Purpose |
|---|---|
s-gw CLI |
Setup, credential enrollment, approvals, policies, agent snippets, guard mode, and diagnostics. |
s-gw-mcp |
Stdio MCP server for agent-facing handle discovery and request creation. |
| Native macOS app | Approval queue, credential inventory, policy rules, usage flow, activity, and audit review. |
| Menu-bar helper | Fast visibility into pending approvals and local daemon status. |
| Local web console | Browser-accessible fallback UI bound to 127.0.0.1. |
| Guard mode | Launch agents with credential-looking environment values replaced by s-gw handles. |
Quick Start
Requirements: Node.js 20 or newer.
npm install -g @s-gw/s-gw
s-gw setup
s-gw status
To build from source, use a stable Rust toolchain. Building the native macOS surfaces also requires a Swift toolchain.
git clone https://github.com/sgateway/s-gw.git
cd s-gw
npm ci
npm run build
npm link
s-gw setup
s-gw status
s-gw setup generates local unlock material, stores it in the operating system credential store, initializes the encrypted ledger, and starts the local UI surfaces available on the current platform.
Add a credential from your terminal without placing the value in chat or a process argument:
printf '%s' "$MY_API_TOKEN" | s-gw secret add-keychain \
--name demo-token \
--type api-token \
--value-stdin \
--inject-env API_TOKEN \
--allow-command "$(command -v printenv)"
Then inspect the non-secret handle metadata:
s-gw secret list
The end-to-end trust loop walks through a disposable request, local approval, execution, and output sanitization without touching a real credential.
Agent Integration
List the known agent profiles and render the configuration for one client:
s-gw agent list
s-gw agent mcp-snippet codex
s-gw agent mcp-snippet claude-code
s-gw agent mcp-snippet opencode
For CLI agents, guard mode can replace credential-looking launch environment values with s-gw handles before the agent starts:
s-gw run codex --dry-run -- -v
s-gw run codex -- --ask-for-approval never
MCP registration does not intercept every prompt, file read, shell, or environment variable. See agent integration and the agent profile matrix for the supported paths and current limitations.
Example Request Flow
- An agent sees
s-gw:credential:prod-readonlyand asks to runaws sts get-caller-identity. - s-gw creates a pending request with the agent name, command, handle, environment binding, working directory, target, and policy result.
- You approve once, for a time window, for the login session, or deny it.
- s-gw starts the approved local process with the credential injected into the requested environment variable.
- s-gw scans the process output before it returns to the agent.
The model can complete the task without receiving the raw access key.
Platform Status
| Platform | Status | Credential store | User interface |
|---|---|---|---|
| macOS 14+ | Primary development platform | Keychain | Native app, menu helper, local web console |
| Windows 10/11 | Preview | Credential Manager | PowerShell client, tray helper, local web console |
| Linux | Experimental CLI | Environment-provided unlock material | Local web console |
Preview installers are available from GitHub Releases. The macOS DMG is ad-hoc signed and unnotarized, and the Windows package is unsigned preview software. Build the same artifacts locally with npm run build:installers.
Security Model
s-gw is designed to reduce accidental credential exposure to coding agents. It does not protect against a compromised operating system account, a malicious approved executable, screen capture, kernel-level access, or every transformed derivative of a secret.
Read the threat model before relying on s-gw for sensitive workflows. Report suspected vulnerabilities through GitHub private vulnerability reporting, not a public issue.
Project Status
- Public source distribution is preview quality.
- macOS is the primary development and test platform.
- Windows Credential Manager support is present but still needs broader native QA.
- Linux currently depends on environment-provided unlock material.
- Desktop preview downloads are unsigned and intended for evaluation.
- The repository is prepared for open-source collaboration, but security-sensitive changes should come with focused tests and threat-model updates when behavior changes.
Documentation
- Documentation index
- Quick start and trust-loop demo
- Architecture
- Threat model
- Agent integrations
- Credential stores and 1Password
- Deployment and packaging
- Third-party assets and licenses
Contributing
Issues and focused pull requests are welcome. Start with CONTRIBUTING.md, and use SECURITY.md for anything that may expose credentials or bypass approval.
License
Apache-2.0. See LICENSE and NOTICE. Third-party names and artwork remain the property of their respective owners and are documented in TRADEMARKS.md and the third-party notices.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.