A council of 49 specialist agents plus 93 tools for every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf): deterministic agents that optionally upgrade to LLM, a self-learning router, cross-CLI memory, and guards against dependency hallucination and decision drift.
Visit mcp-server This is mine — claim it
Source: https://github.com/jigyasudham/veto
Listing URL: https://wingmanprotocol.com/mcp/servers/veto/
Show your listing is live — the card backlinks here and picks up the verified badge automatically once you claim it.
<iframe src="https://wingmanprotocol.com/embed/card/veto" width="340" height="170" style="border:0;border-radius:10px" loading="lazy" title="Veto — live on WingMan Protocol"></iframe>
Or the one-line script:
<script src="https://wingmanprotocol.com/embed/card.js" data-slug="veto" async></script>
Or a README badge:
[](https://wingmanprotocol.com/directory/veto?utm_source=badge)
Visual feedback loop for AI coding agents: stakeholders drop pins on the live app (selector, screenshot, DOM snippet, thread, acceptance criteria); the agent re
Multi-agent coordination bus over MCP: atomic gap-free claims, advisory file leases, a shared event ledger, presence, prose handoffs, and a task graph so multip
Security & trust layer for AI agents: scans an MCP server or skill before install for exfiltration, prompt-injection sinks, dangerous capabilities and obfuscati
Socket.IO-style telemetry for MCP servers: instrument a tool call and stream its live progress (steps, logs, cost, done) to any connected MCP client via notific
Indexes a TypeScript/React repo (including monorepos) into a queryable code graph: reverse queries, blast-radius analysis, dependency cycles, dead-code orphans,
Stateful, structured, auditable shell sessions for AI agents over local, SSH, and Docker, with secret redaction, output budgeting, SSH host-key verification, an