MCP.Market

s-gw MCP server

by sgateway·io.github.sgateway/s-gw·v0.1.22·15 stars
No reviews yet

Keep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.

A89/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

15 stars151 downloads/wk

Reviews

Write one

Nobody has reviewed s-gw yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

s-gw tools (10, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • sgw_describe_handle

    Show non-secret metadata for one local secret handle.

  • sgw_execute_requestwrite action

    Execute a previously approved local request and return sanitized output.

  • sgw_list_handles

    List known local secret handles and non-secret metadata.

  • sgw_request_executionwrite action

    Create a pending local manifest for a command that needs one secret injected as an environment variable.

  • sgw_request_http

    Request an approved HTTPS operation executed by s-gw. Credentials remain outside the agent.

  • sgw_request_ssh_sessionwrite action

    Create a local approval request for an SSH command. Unix-like systems use an s-gw-owned ControlMaster; Windows uses a hardened one-shot ssh.exe command with an SSH private key.

  • sgw_request_ssh_transferwrite action

    Request an SSH upload from the agent workspace. Approval binds the source contents and remote destination.

  • sgw_run_executionwrite action

    Run a command through reusable local approval without creating a ledger record for every invocation.

  • sgw_scan_file

    Scan a local file for secrets and return tokenized text plus local handles. Raw values are not returned.

  • sgw_scan_text

    Scan supplied text and return tokenized text. Persist=false previews handles without enrolling secrets.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

no findings
  • Code scan89 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How s-gw compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 80% of 48,255 servers
Tools
10
the typical server has 7
Tools that change things
50%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
15
more than 90% of 28,688 servers
Downloads a week
151
more than 71% of 12,191 servers with a package

What its tools let an agent do: 5 read · 5 change

Release history: 2 versions in the registry since 2026-08-13, latest 2026-10-06, typically one every 54 days.

Install s-gw in Claude Code, Cursor or VS Code

Runs npx -y @s-gw/s-gw on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add s-gw -- npx -y @s-gw/s-gw
Add to Cursor

What the publisher says

From the s-gw repository's README, as published. We do not edit it. Read it on GitHub

s-gw

Local credential control for coding agents. Approve bounded actions locally. Keep raw credentials out of model context and tool output.

Demo · Downloads · Quick start · Documentation · Security · Contributing

Stop handing raw credentials to coding agents. s-gw gives agents typed handles, asks you to approve bounded local actions, resolves the credential inside a constrained process on your machine, and returns sanitized output instead of secret values.

[!IMPORTANT]

s-gw is an early preview. Storage formats and interfaces may change, Windows and Linux desktop 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.

The TypeScript broker, clients, and documentation in this repository are Apache-2.0 licensed. Distributed packages also contain a proprietary compiled Rust execution core whose source is maintained separately.

The Short Version

  • Agent sees: s-gw:credential:prod-readonly
  • You approve: agent, command, handle, environment binding, working directory, and target
  • s-gw runs: the command locally with the credential injected only into that child process
  • Agent receives: sanitized output, audit evidence, and no raw secret

If s-gw helps your agent workflow, star the project. It makes the preview easier for other developers to find.

See It In Action

The local console shows the approval queue, credential inventory, policy state, usage flow, and activity history without exposing secret values.

Public demo: s-gw.com.

What It Does

Why Teams Use It

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

s-gw: common questions

Is s-gw MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the s-gw safety report
How do I install s-gw?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does s-gw need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is s-gw maintained?
The last commit was 2 days ago (2026-11-02). The latest release is v0.1.22.
What can I use instead of s-gw?
Servers from other publishers that do the same job: SSH Manager MCP server, SSH — policy-gated remote access MCP server and Tradememory Protocol MCP server. Compare all s-gw alternatives.
How does s-gw compare with other MCP servers?
safety score 89/100 (higher than 80% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to s-gw

Same job from other publishers: the closest match first, then the best rated.

All s-gw alternatives →
  • SSH Manager
    SSH for AI agents: commands, files, backups and health, with approval, a vault and an audit trail
    A
  • SSH — policy-gated remote access
    Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.
    B
  • Tradememory Protocol
    Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
    B