claude-flow
Verified · 18 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Sanction
Verified · 34 days agoApproval and budget checks before agent spending or tool use. Cooperative MCP; host must ask.
Install
claude mcp add --transport http sanction https://getsanction.com/mcp
Our take
Sanction is a control layer for AI agents that need approval gates around spending and credential use, with budgets, vaulting, and audit features. It is for teams building agents that can trigger real-world actions and want tighter operational guardrails. The direction is sensible, but this is a sensitive trust surface, so the low maturity signal means it deserves careful security review before deployment.
Verification record
- 34 days ago
- 2
- 34 days ago
- no
- NOASSERTION
- 233
- 0.9.0
- 2026-07-15
More in ai
browse all →tldraw
Verified · 19 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 9 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · yesterdayOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
mobilerun
Verified · 21 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 8 days agoAI Agents Framework with Self Reflection and MCP support