io.github.SoWhatI/vaultshellai

vaultshell

Verified · today

Injects secrets into shell commands at exec time; plaintext never reaches the LLM context

Install

claude mcp add vaultshell -- docker run -i --rm ghcr.io/sowhati/vaultshell:0.1.2

Our take

Injects secrets into shell commands at execution time so plaintext credentials do not enter the LLM context. It is for security-conscious agent workflows that need command execution with secrets, but because it sits on a sensitive boundary, it deserves careful review before production use despite having an OCI package.

reviewed by hand · 2026-10-01

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
1
last commit
today
archived
no
license
MIT
in registry since
2026-09-30

github.com/SoWhatI/vaultshell

More in ai

browse all →
claude-flowai

claude-flow

Verified · 13 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 13 days ago

tldrawai

tldraw

Verified · 14 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 14 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 4 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 4 days ago

openmetadata-mcpai

OpenMetadata

Verified · 32 days ago

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked 32 days ago

mobilerunai

mobilerun

Verified · 16 days ago

Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.

hand-reviewed9.4k starschecked 16 days ago

praisonaiai

PraisonAI

Verified · 3 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed9.1k starschecked 3 days ago