Spec Driven Development
von formulahendry
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Läuft auf deinem Computer★ 440MITAktualisiert vor 14 Monaten
Installieren
Tokonomix Council
Überblick
Beschreibung vom Entwickler (englisches Original)
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
Die drei Säulen von PopNx MCP
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
- Stimmen der NutzeriNoch keine BewertungenBewertungen starten in einem späteren Schritt zusammen mit Benutzerkonten
- Unsere Basischecksi1 von 1 bestandenAnhand öffentlicher Informationen geprüft; Code noch nicht gescannt
- NutzungiNoch nicht gemessen★ –
Was du damit machen kannst
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
- Verbindung: Läuft auf deinem Computer
- Transport: stdio
- Kategorie: Sonstiges
- Das musst du eintragen: TOKONOMIX_API_KEY
Installation
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Bevor du installierst
- Basischecks: 1 von 1 bestanden
- Läuft auf deinem Computer mit den Rechten deines Benutzerkontos (Dateien, Netzwerk, Apps).
- Das trägst du selbst ein:
TOKONOMIX_API_KEY
Als geheim markierte Werte sind Schlüssel zu deinem Konto. Gib sie nie weiter und füge sie nie in einen Chat ein.
Du brauchst
- npmNode.js installiert (für den Befehl npx)
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"council": {
"command": "npx",
"args": [
"-y",
"tokonomix-council-mcp"
],
"env": {
"TOKONOMIX_API_KEY": "your-value"
}
}
}
}Führe das in deinem Terminal aus
claude mcp add council --env TOKONOMIX_API_KEY=your-value -- npx -y tokonomix-council-mcpTrag die leeren Werte ein, bevor du ihn startest.
Oder kopier die Einstellungen selbst
In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"council": {
"command": "npx",
"args": [
"-y",
"tokonomix-council-mcp"
],
"env": {
"TOKONOMIX_API_KEY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Oder kopier die Einstellungen selbst
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"council": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tokonomix-council-mcp"
],
"env": {
"TOKONOMIX_API_KEY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Werte, die du selbst einträgst
- Tokonomix API key (tok_live_...). Optional - keyless onboarding works without it.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Was er kann
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Basischecksi
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026
- ✓ Bestanden
Entwickler passt zum Repo
Der Registry-Name wurde über die Domain tokonomix.ai bestätigt (die Registry prüft, wem die Domain gehört)
- … Noch nicht geprüft
Wird noch gepflegt
Dieses Repo haben wir noch nicht von GitHub gelesen
- … Noch nicht geprüft
Hat eine Lizenz
Dieses Repo haben wir noch nicht von GitHub gelesen
- – Nicht zutreffend
Endpunkt antwortet
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
- – Nicht zutreffend
Anmeldung mit OAuth
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
- … Noch nicht geprüft
Keine versteckten Anweisungen in Tool-Beschreibungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Im Vergleich mit anderen in Sonstigesi
- Mehr Sterne als 0 % der anderen 32680 Server in dieser Kategorie
- Neuer in der Registry veröffentlicht als 51 % der anderen 32680 Server in dieser Kategorie
- Basischecks gleich gut wie oder besser als bei 100 % der anderen 32680 Server in dieser Kategorie
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Häufige Fragen
Ist Tokonomix Council sicher?
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Welche Schlüssel oder Codes braucht er?
Das musst du eintragen: TOKONOMIX_API_KEY
Läuft er auf meinem Computer oder in der Cloud?
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Wird er noch gepflegt?
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (1.14.0) kam vor 39 Tagen in die Registry.
Welche Apps können ihn nutzen?
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Node.js auf deinem Computer.
Was kann ich stattdessen nutzen?
In derselben Kategorie: Spec Driven Development, Remote Desktop Commander, EmbeddedCI BenchPod
Alternativen
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
Remote Desktop Commander
von desktop-commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Läuft in der Cloud★ 211Aktualisiert vorgestern
Installieren
EmbeddedCI BenchPod
von embeddedci-com
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
Läuft auf deinem ComputerAktualisiert heute
Installieren
README vom Entwickler
README öffnen
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
tokonomix-council-mcp
A multi-model consensus MCP server — cross-vendor proposers, an independent judge, and blind-spot/disagreement detection for high-stakes AI decisions. An open reference implementation of AI Decision Engineering — a discipline we are proposing, not yet an external standard.
Mission. *Help autonomous systems make better decisions by combining independent expert reasoning instead of trusting a single model.*
In 20 seconds: *Important AI decisions deserve more than one opinion.*
The Tokonomix ecosystem (where Council fits)
Council is one specialized component in a larger stack. Each owns exactly one responsibility, so they compose cleanly:
Execution → ANS (run a backlog to completion, unattended)Decision → Council (independent review → grounded decision) ◀── this repo Verification → Media QC (image / video / document output quality) Measurement → Benchmark (intelligence tests, arena, reputation) Routing → Router (which provider/model hosts a call) Memory → Memory (durable context across sessions) Safety → Safety (policy / guardrail enforcement)
Council owns one box: the decision. It does not execute, schedule, route, or remember — those live in their own components (details below).
Status — what is live right now
So you never call something that isn't there yet. Server-gated features can be off for your account/tier; when they are, the tool returns a clear "not enabled" message instead of erroring.
| Capability | Status |
|---|---|
tokonomix_consensus_ask — modes consensus / diff / best_of / raw / full | Live |
tokonomix_single_ask — single-model passthrough | Live |
tokonomix_list_models, tokonomix_get_balance | Live |
tokonomix_skill_version, tokonomix_get_skill | Live |
tokonomix_onboard, tokonomix_onboard_verify — keyless first-run | Live |
tokonomix_rate_consensus — agent rating / feedback-loop | Live (platform-gated) |
tokonomix_relay_human_feedback — human verdict channel | Live (platform-gated) |
Vision input (images on ask) | Live |
tokonomix_upload + context.session/handles — large shared context-pack | Account-gated (on for eligible accounts) |
context.inline / context.github_refs grounding | Live (account-gated) |
Grounding-gate (needs_context refusal of thin input) | Gated (shadow-first rollout) |
| Reranking, web-search plugin | Planned |
Council MCP exists to improve decision quality, not to chat, generate, or route. The governing idea is simple:
### Consensus × Ground Truth = Decision Quality
Consensus is one mechanism for decision quality — not the whole of it. Grounding (checking a claim against the real artifact) is the strongest lever, stronger than adding more models; judge-independence and verification are mechanisms too. Several independent expert models assess the same problem in parallel and blind, an independent, cross-family judge reconciles their findings, and grounding ties the whole thing to reality — so you get one decision you can act on, with the disagreements a single model would have hidden surfaced rather than smoothed away. **Consensus is a *means*; better decisions are the goal.**
It is not a chatbot, a model, an LLM, a prompt library, a multi-model chat, a voting system, or an averaging system. It does not make any model smarter, and it does not pick a winner by majority — it changes how multiple independent models' outputs become *one defensible decision*.
What it honestly buys you — and what it does not. Across our own validation (see Benchmarks), the council ties the best single model on clean accuracy and beats it nowhere, and on a SWE-bench bug-detection run it showed no measurable net uplift in catch rate over re-running a single agent. So we do not claim "more accurate" or "catches more bugs" anywhere. What it does buy is variance-elimination (you stop gambling on which single model you happened to ask), a verification / agent-QA layer, judge-independence, EU data residency, and grounding. Read When consensus helps / doesn't / can hurt before you rely on it — that section is the point, not a disclaimer.
Works with Claude Code, Cursor, Cline, Continue, and Zed. One npx line to install.
### Principles of Decision Engineering
The discipline Council implements rests on ten principles. An autonomous system should:
1. Verify before acting — a decision is provisional until it has been checked.
2. Preserve disagreement — the lone dissent is often the finding that mattered; never average it away.
3. Separate execution from judgement — the thing that *does* the work should not also be the thing that *grades* it.
4. Separate reasoning from verification — generating an answer and checking it are different jobs.
5. Separate confidence from correctness — a model's tone is identical whether it is right or wrong.
6. Prefer evidence over agreement — agreement measures agreement, not truth; ground the claim.
7. Expose uncertainty — surface what was *not* settled, don't hide it behind one confident answer.
8. Make decisions auditable — record who proposed, who judged, what it cost, on what input.
9. Remain reproducible — the same input and method should be re-runnable to the same finding.
10. Never hide failure modes — a decision tool that conceals when it fails is not a decision tool.
What Council owns — and what it explicitly does not
Council is a Decision Engineering layer. Its scope is deliberately narrow, because a clear boundary is what makes a component trustworthy to compose with.
Council owns DECISIONS ONLY:
- decision quality and decision confidence,
- independent review and reasoned consensus,
- verification of reasoning and claims,
- grounding (checking a claim against the real artifact),
- disagreement analysis,
- judge independence,
- auditability of how a decision was reached.
Council is explicitly NOT responsible for: execution, workflow, task scheduling, agent autonomy, long-term memory, provider routing, or browser automation. Those are real responsibilities — they simply live in other components.
- Need something executed (a backlog run to completion, unattended)? That is [Agents Never Sleep (ANS)](https://github.com/TokonoMix/agents-never-sleep), the execution governor. ANS is the worker/governor; Council is the verifier it can delegate a decision to. Council does not run, schedule, or remember work.
See Council in the Tokonomix ecosystem for where every adjacent responsibility lives.
Why Council exists (the short story — for a human OR an AI agent)
Why does Council exist? Because important AI decisions are made by single models that answer with total confidence and never tell you what they didn't consider. For chat that is fine; for a security review, a migration, a GDPR interpretation, or a legal clause, a confidently-wrong decision is expensive and you find out too late.
Why is one model not enough? A single model is one opinion with one blind spot. *Which* model is strongest is not stable — it shifts per task, per domain, per bug class. Standardise on the wrong one and you ship real defects without ever seeing a disagreement.
When does combining models help? When errors are *uncorrelated*: different vendors are wrong about different things, so you only need one of them to catch the timing side-channel or the missed edge case for it to surface. That decorrelation only exists across vendors — a single vendor's "panel" shares its own training data and blind spots.
When does it NOT help? On routine work (renames, formatting, lookups) and on easy tasks any strong single model already saturates. There the council only adds cost and noise — use a single model.
Why does grounding matter more than more models? Because agreement measures agreement, not truth. Ungrounded, frontier models can agree *and be uniformly wrong* (they share training data). Feeding the council the real artifact — the literal file, diff, spec, logs — is the lever that turns "they agreed" into "they checked it against reality." More models cannot fix a shared blind spot; grounding can.
Why does judge independence matter? Because a judge that also wrote one of the answers scores its own work and *inflates* agreement (LLM self-preference is real and measured). A disjoint, cross-family judge is the only honest reconciler.
Why do failure modes matter? Because consensus *can* be worse than a single model — lossy synthesis, correlated failures, false consensus, specialist overlap. A decision tool that hides its failure modes is not a decision tool. Honesty about when consensus does NOT work is the competitive advantage, not a caveat we bury.
Contents
- Why Decision Engineering is becoming necessary
- Why LLMs cannot solve this themselves
- Design principles
- A story: the security review
- The problem
- Why single-model review falls short
- How Council works
- Architecture
- The consensus process
- The judge
- When consensus helps / doesn't / can hurt
- Decision Engineering vs existing techniques
- Council in the Tokonomix ecosystem
- Practical examples
- Installation
- Integration & API surfaces
- Benchmarks
- Glossary
- FAQ
- Roadmap
Going deeper: this README is the field guide. The full argument — why the field exists, the design principles, the failure modes, why one model is insufficient, why consensus *alone* is insufficient, why grounding is necessary, and why a human stays ultimately accountable — lives in the [Decision Engineering Manifesto](https://github.com/TokonoMix/tokonomix-council-mcp/blob/main/docs/decision-engineering-manifesto.md). The README links out rather than duplicating that depth.
Why Decision Engineering is becoming necessary
Every time software took on more responsibility, a new discipline appeared to keep it trustworthy — not because engineers got worse, but because the cost of an unchecked output got higher:
| Software gained… | …so we invented |
|---|---|
| Code that ran unattended | Testing — prove it does what we think |
| Many people committing | Continuous Integration — catch breakage on every change |
| Code too large to hold in one head | Code Review — a second pair of eyes before merge |
| Subtle, repeating defect classes | Static Analysis — a machine that flags them automatically |
| Systems shipping continuously | DevOps — make deployment itself safe and observable |
| Models that now make decisions | Decision Engineering — make the *decision* itself re
Nur der Anfang wird gezeigt; den Rest findest du im Repo