Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/RIPRODUCTIONS/wingman-agent-gatewayWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/riproductions/wingman-agent-gateway/gateway)<a href="https://agentmods.dev/mcp/riproductions/wingman-agent-gateway/gateway"><img src="https://agentmods.dev/badge/mcp/riproductions/wingman-agent-gateway/gateway/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/riproductions/wingman-agent-gateway/gateway"><img src="https://agentmods.dev/badge/mcp/riproductions/wingman-agent-gateway/gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gateway scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"gateway": {
"url": "https://wingmanprotocol.com/mcp",
"type": "streamable-http"
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 6 lines scan A 0b639d1e2600
gateway is an MCP server published in the GitHub repository RIPRODUCTIONS/wingman-agent-gateway (3 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
nautilus-compass
MCP server "nautilus-compass" as configured in chunxiaoxx/nautilus-compass. Runs ~/.claude/plugins/nautilus-compass/mcp_server.py with python3. Needs 2 environment variables to run.
cogmemory-mcp
CogMemory MCP Server — Unified context subsystems for AI coding agents. Runs locally from the cogmemory-mcp npm package.
aura
Email address, webhook, durable memory and zero-token waiting for agents. Paid in USDC via x402. Remote server at aura.rohnelt.dev.
contextful
Efficient context management: code search, evidence packs, and memory for coding agents. Runs locally from the @inferensys/contextful npm package.
mnemo
MCP server "mnemo" as configured in oyekamal/mnemo-agent. Runs mnemo.mcp_server with ${CLAUDE_PROJECT_DIR:-.}/.venv/bin/python. Needs 1 environment variable to run.
agent-loop-mcp
Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp. Runs locally from the @mhrj/mcp-agent-loop npm package.