claude-flow
Verified · 16 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
heimdall
Verified · 31 days agoScan an MCP server or agent config for injection, exfiltration, and risky capabilities.
Install
claude mcp add heimdall -- npx -y [email protected]
Our take
Heimdall scans MCP servers or agent configs for prompt injection, exfiltration paths, and other risky capabilities. It is for developers and security reviewers who want a lightweight audit pass on agent tooling before deployment. The purpose is concrete and relevant, but security scanners live or die by rule quality and update cadence, so the low maturity signals suggest using it as a helpful check rather than a definitive assessment.
Verification record
- 31 days ago
- 0
- 3 mo ago
- no
- MIT
- 65
- 0.5.1
- 2026-07-05
More in ai
browse all →tldraw
Verified · 17 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 7 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 35 days agoOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
mobilerun
Verified · 19 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 6 days agoAI Agents Framework with Self Reflection and MCP support