Brings eight specialized security agents to your IDE to tear apart Solidity and Anchor contracts before you deploy them. The MCP server exposes audit, generation, and vulnerability fix tools. Drop it into Claude Desktop or Cursor, point it at your contract, and get a graded exploit report testing for reentrancy, flash loan manipulation, oracle attacks, access control gaps, and five other classes. Works across Ethereum, Polygon, Base, Arbitrum, Optimism, BSC, Avalanche, and Solana. Paid calls cost $5 per audit via x402 USDC on Base. Generation and compilation are included, fixes are free. If you're shipping anything with transferFrom or external calls, this catches what vibes-based severity scores miss.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent