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.
/plugin marketplace add religa/multi_mcpnpx agentmods add plugins/religa/multi_mcp/marketplacegit clone --depth 1 https://github.com/religa/multi_mcpGrade A, and why
multi_mcp 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 2d 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
{
"name": "multi_mcp",
"owner": {
"name": "Multi-MCP Team",
"email": "[email protected]"
},
"metadata": {
"description": "Multi-model AI orchestration MCP server",
"version": "0.1.1",
"homepage": "https://github.com/religa/multi_mcp"
},
"plugins": [
{
"name": "multi-mcp",
"source": "./",
"description": "Code review, compare, and debate tools using multiple AI models",
"version": "0.1.1",
"license": "MIT",
"category": "code-review",
"keywords": [
"mcp",
"code-review",
"multi-model",
"llm",
"ai",
"ai-code-review",
"anthropic",
"claude",
"claude-mcp",
"code-analysis",
"developer-tools",
"gemini",
"gpt",
"llm-orchestration",
"model-context-protocol",
"multi-agent",
"openai"
],
"mcpServers": {
"multi": {
"command": "uvx",
"args": [
"multi-mcp"
]
}
}
}
]
}
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.
- 2d ago First seen · 50 lines scan A 950afafe905b
multi_mcp is a plugin published in the GitHub repository religa/multi_mcp (35 stars, last pushed 19d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
ouroboros
Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the…
ouroboros
Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the…
stuntman
Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model (DeepSeek, Groq, Ollama, Grok, Kimi… via a local proxy or opencode), OpenAI's Codex CLI, Google's Antigravity CLI (agy), or Meta's Muse Code CLI, review with Claude — your subscription tokens go only where intelligence matters.
stuntman
Plugin marketplace listing 1 plugin: stuntman.
idea-factory
Turn Claude Code into a virtual startup — describe your idea in one line and a team of AI agents builds the MVP autonomously.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.