The High Council runs on your own machine — the client starts it, so there is no endpoint to ping. 298 installs a week from npm. Last commit 8 Oct 2026.
Several models from different labs plan in a blind proposal, debate and review loop. Your own keys.
We read the source, 7 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(process.execPath, [cli, ...args], {
for (const [k, v] of Object.entries(process.env)) if (/^\$\{user_config\.[^}]*\}$/.test(v || '')) delete process.env[k];
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add the-high-council -- npx -y the-high-council
{
"mcpServers": {
"the-high-council": {
"args": [
"-y",
"the-high-council"
],
"command": "npx"
}
}
}
[mcp_servers.the-high-council]
command = "npx"
args = ["-y", "the-high-council"]
{
"mcpServers": {
"the-high-council": {
"args": [
"-y",
"the-high-council"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"the-high-council": {
"args": [
"-y",
"the-high-council"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ANTHROPIC_API_KEY (Your own Anthropic API key. Needed only by chains that seat Anthropic models.), OPENAI_API_KEY (Your own OpenAI API key. Needed only by chains that seat OpenAI models.), GOOGLE_API_KEY (Your own Google (Gemini) API key. Needed only by chains that seat Google (Gemini) models.), MISTRAL_API_KEY (Your own Mistral API key. Needed only by chains that seat Mistral models.), DEEPSEEK_API_KEY (Your own DeepSeek API key. Needed only by chains that seat DeepSeek models.), GROQ_API_KEY (Your own Groq API key. Needed only by chains that seat Groq models.), TOGETHER_API_KEY (Your own Together API key. Needed only by chains that seat Together models.), COHERE_API_KEY (Your own Cohere API key. Needed only by chains that seat Cohere models.), OPENROUTER_API_KEY (Your own OpenRouter API key. Needed only by chains that seat OpenRouter models.), ZAI_API_KEY (Your own Z.ai API key. Needed only by chains that seat Z.ai models.), MAX_USD_PER_RUN (Per-run spend ceiling in US dollars. The run stops before any stage that could pass it. Default 7.), COUNCIL_MAX_USD_LIMIT (A hard per-run ceiling in US dollars that the MCP client cannot raise or remove (max_usd above it, or "none", is refused). Set it to the same value as MAX_USD_PER_RUN to lock the cap.), COUNCIL_WORKDIR (Folder for task files and run output. Default: the directory the client starts the server in.).
The author declared them in the registry entry; get the values from the project itself.
Join a lab where AI agents from different people debate in turns and refute each other.
Discover available AI models and delegate analysis or code review from your existing agent.
Code review by AI models from different companies, usually two. Shows where they agree and disagree.
Run AI agent evaluations on your own model keys, and publish runs others can review and re-run.
Memory for agents and people: exact recall from a plain-text index, by your own keys.
GitLab over MCP from your own account: issues, merge requests, reviews, the repository and CI.
Search the Crela software marketplace and publish, update and review your software from your agent.
Prepare pump.fun token launches from your AI agent. You review and sign each one in your own wallet.
Answers built from our own checks of this server.