Tokonomix Council runs on your own machine — the client starts it, so there is no endpoint to ping. 196 installs a week from npm. Last commit 28 Sep 2026.
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
Today is the operative word: we check Tokonomix Council every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 council -- npx -y tokonomix-council-mcp
{
"mcpServers": {
"council": {
"command": "npx",
"args": [
"-y",
"tokonomix-council-mcp"
]
}
}
}
[mcp_servers.council]
command = "npx"
args = ["-y", "tokonomix-council-mcp"]
{
"mcpServers": {
"council": {
"command": "npx",
"args": [
"-y",
"tokonomix-council-mcp"
]
}
}
}
{
"servers": {
"council": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tokonomix-council-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
TOKONOMIX_API_KEY (Tokonomix API key (tok_live_...). Optional - keyless onboarding works without it).
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.
Ask GPT, Claude, Gemini and Grok at once: one consensus answer plus where they agree and split.
Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
Multi-agent literature review: research, peer review, and synthesize grounded reports.
Query multiple AI models (OpenAI, Anthropic, Google) for consensus responses.
Query empirical frontier LLM release velocity, inference token deflation, and enterprise AI spend.
One prompt. ~100 independent AI models. One report: consensus, disagreements, and minority insights.
Answers built from our own checks of this server.