io.github.bazingaedward/keygrantai

keygrant

Verified · today

Run commands with API keys injected per call — values never enter model context.

Install

claude mcp add keygrant -- uvx keygrant

Our take

Runs commands with API keys injected per call while keeping secret values out of model context. It is for users who need assistants to operate credentialed tools with tighter secret-handling boundaries. Because it sits near sensitive execution and credentials, it deserves careful local review despite the sensible design goal.

reviewed by hand · 2026-10-09

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
0
last commit
today
archived
no
license
Apache-2.0
in registry since
2026-10-08

github.com/bazingaedward/keygrant

More in ai

browse all →
claude-flowai

claude-flow

Verified · 21 days ago

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

hand-reviewed73k stars19k dl/wkchecked 21 days ago

tldrawai

tldraw

Verified · 22 days ago

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

hand-reviewed50k starschecked 22 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 12 days ago

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

hand-reviewed45k stars12k dl/wkchecked 12 days ago

openmetadata-mcpai

OpenMetadata

Verified · 4 days ago

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

hand-reviewed15k starschecked 4 days ago

mobilerunai

mobilerun

Verified · 24 days ago

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

hand-reviewed9.4k starschecked 24 days ago

praisonaiai

PraisonAI

Verified · 11 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed9.1k starschecked 11 days ago