Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
Council is one specialized component in a larger stack. Each owns exactly one responsibility, so they compose cleanly:
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Tokonomix Council is connected, these are the calls the assistant has available:
Independence — proposers answer blind and in parallel; the judge is disjoint from them and cross-family. No model grades its own workAuditability — every decision returns who proposed, who judged, and what it cost, so it can be reconstructedTransparency — what was not settled is surfaced (the blind-spots section, the diff map), never hidden behind one answerReproducibility — the same input + method re-runs to the same finding; record the models and date, because the default council can changeTraceability — a request_id and a billing breakdown tie a stored decision back to exactly how it was producedProposers — the 2–6 models that answer the prompt. Chosen for cross-family decorrelation, not just raw score. Empirically selected from Tokonomix's ownJudge — disjoint from the proposers by default, cross-family, never scoring its own answer. Budget is auto-sized to the proposer countGateway — runs the orchestration, applies region/residency policy, meters cost, returns one result with a billing breakdown and a request_id. The gatewayPer — key policy** — budget caps, default council/route, and allow-lists are set on the API key, not re-decided per call, so an unattended run can'tCapability — StatusThis listing has no verified copy-paste launch configuration. Use the project documentation to confirm the entry point, runtime and authentication before registering it in your MCP client. A package name or repository alone is not a runnable configuration.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Payments infrastructure meets AI — customers, invoices, subscriptions and current API docs from Stripe's server.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.
Build for Shopify with current APIs — the official Dev MCP server for schema-accurate storefront and admin code.
Give your AI assistant a supervised window into your Interactive Brokers account — balances, positions, live quotes and orders.
Invoices, payments and disputes through PayPal's official server — commerce operations by conversation.