vnmoorthy

Local-first proxy and trace viewer for the Model Context Protocol (MCP). See every JSON-RPC message your AI agents send.

Immune — the agent security loop that turns every attack into an antibody. MCP firewall → replayable breach trace in ClickHouse → synthesized countermeasure → replay-proven → Semgrep rescan → signed receipt → ruling → the next agent is immune. Built at the Cyberdefense Hackathon, SF Tech Week 2026.

Pioneer: the stop signal for agents. When an agent fails on a product, the next one is warned and gets the fix, and the vendor sees where agents fail. Postgres-native, MCP, built at Supabase Select 2026.

The auction house for AI agents. Shopping agents call one MCP tool, merchants bid live, and every bid is verified against the merchant's real checkout. Liars are withdrawn, offers rank on merit and fees never buy rank. Spending limits, human approval by text (Inkbox) and a double-entry ledger. Built with mcp-use.

🛡️ The consent firewall for AI agents. Your agent can use the world's public data — the world can't use yours. Field-level minimization, in-flow consent, LLM tokenization, prompt-injection quarantine & hash-chained privacy receipts. MCP server included.

🧵 Self-healing web data pipelines — an agent that detects scraper breakage, synthesizes validated selector repairs, and ships them only through a human approval gate. Built on TrueForge + Bright Data.