REA
Verified · 6 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
TAP
Verified · 38 days agoCredential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Install
claude mcp add --transport http tap https://mcp.tap.human.tech/mcp
Our take
TAP is a security-oriented MCP server for isolating credentials, enforcing policy checks, and optionally requiring human approval before sensitive actions. It is best suited to teams deploying agents in real environments where secret handling and action gating matter more than raw convenience. The design goal is credible and timely, but the public maturity signal is still light, so it looks more like an emerging control layer than a settled standard.
Verification record
- 38 days ago
- 12
- 3 mo ago
- no
- Apache-2.0
- 2026-07-24
More in ai
browse all →claude-flow
Verified · 35 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
tldraw
Verified · 36 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 26 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 18 days agoOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
mobilerun
Verified · 38 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.