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/salutaris91/llm-council-mcp-serverWrote 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/salutaris91/llm-council-mcp-server/llm-council-mcp-server)<a href="https://agentmods.dev/mcp/salutaris91/llm-council-mcp-server/llm-council-mcp-server"><img src="https://agentmods.dev/badge/mcp/salutaris91/llm-council-mcp-server/llm-council-mcp-server/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/salutaris91/llm-council-mcp-server/llm-council-mcp-server"><img src="https://agentmods.dev/badge/mcp/salutaris91/llm-council-mcp-server/llm-council-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
llm-council-mcp-server 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 12d 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
{ "llm-council-mcp-server": { "command": "uvx", "args": [ "llm-council-mcp-server" ] } }
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.
- 12d ago First seen · 8 lines scan A ba5942e961d1
llm-council-mcp-server is an MCP server published in the GitHub repository salutaris91/llm-council-mcp-server (7 stars, last pushed 2mo 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
excalidraw-architect-mcp
An MCP server that generates beautiful Excalidraw architecture diagrams with perfect auto-layout, stateful editing, and architecture-aware component styling. Runs locally from the excalidraw-architect-mcp Python package.
openrouter-agents
MCP server "openrouter-agents" as configured in wheattoast11/openrouter-deep-research-mcp. Runs /var/home/zero/terminals-tech/src/server/mcpServer.js with node. Needs 5 environment variables to run.
mnemosure
Source-grounded memory layer for AI agents — cites its sources, says "I don't know" when it lacks evidence, and corrects superseded facts. MCP-ready. Runs locally from the mnemosure Python package.
stickyinc
MCP server "stickyinc" as configured in Astralchemist/stickyinc. Runs locally from the stickyinc npm package.
or-info
CLI + MCP server for OpenRouter models: prices, benchmarks, context and comparisons. Runs locally from the @aggc/or-info npm package.
modelradar-mcp
MCP server "modelradar-mcp" as configured in legifx/modelradar-mcp. Runs locally from the modelradar-mcp npm package.