claude-flow
Verified · todayAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
mcp-seatbelt
Verified · 20 days agoMCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Install
claude mcp add mcp-seatbelt -- npx -y @kryptosai/[email protected]
Our take
Acts as a security proxy for MCP runtimes, enforcing policies to block risky agent tool calls. It is relevant to developers and operators who want guardrails around agent execution, especially in environments with file system or shell access. The public footprint is still small, but the comparatively stronger download count is a meaningful signal that the problem it addresses is real and that the tool is seeing adoption.
Verification record
- 20 days ago
- 3
- 2 mo ago
- no
- MIT
- 246
- 0.7.1
- 2026-08-04
More in ai
browse all →tldraw
Verified · yesterdayDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 25 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 19 days agoOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
mobilerun
Verified · 3 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 25 days agoAI Agents Framework with Self Reflection and MCP support