llm-bus MCP server
Commit 3. Sept. 2026Koordiniert mehrere AI Agents über ein gemeinsames Event-Ledger, atomare Task-Claims und Advisory File Leases, um Kollisionen zu vermeiden und Handoffs zu verwalten.
Auch bekannt als danieldoderlein/llm-bus
- Stars
- 9
- Tools
- —
- Downloads, 30 Tage
- —
- Neueste Version
- 1.0.0
- Letzter Commit
- 3. Sept. 2026
- Lizenz
- AGPL-3.0
Was ist llm-bus MCP?
llm-bus ist ein MCP server. Koordiniert mehrere AI Agents über ein gemeinsames Event-Ledger, atomare Task-Claims und Advisory File Leases, um Kollisionen zu vermeiden und Handoffs zu verwalten.
Zusammenfassung generiert aus dem README des Projekts
Über llm-bus MCP server
LLM Bus fungiert als Koordinationsschicht für mehrere AI Agents und menschliche Operatoren, um Arbeitskollisionen zu verhindern und Handoffs zu verwalten. Es arbeitet als gemeinsames Backplane über das Model Context Protocol und stellt ein Live-Event-Ledger bereit, in das alle Teilnehmer lesen und schreiben können. Dieses System ermöglicht es Agents, Wissen seitlich zu teilen, anstatt Informationen immer wieder neu abzuleiten, was Tokens und Zeit spart. Nutzer können den Server mit Node.js und PostgreSQL selbst hosten oder einen Managed Service nutzen.
Entwickler interagieren mit dem Server über spezifische MCP Tools, die in Gruppen wie Orientation, Handoffs, Tasks und Leases unterteilt sind. Das System nutzt atomare, lückenlose Claims, um sicherzustellen, dass niemals zwei Agents dieselbe Task-ID beanspruchen, und Advisory File Leases, um zu verhindern, dass Agents die Bearbeitungen des jeweils anderen überschreiben. Der Zugriff wird über Bearer Tokens verwaltet, die projektbezogen sind und spezifischen Teilnehmern zugeordnet werden können. Dieses Setup ermöglicht parallele Agent-Workflows über verschiedene Worktrees oder Branches hinweg, ohne dass ein Mensch den Kontext manuell kopieren muss.
Was du damit machen kannst
- 1Verhindern von Kollisionen bei parallelen EditsEin Agent kann einen Advisory Lease auf eine Datei anfordern, um sicherzustellen, dass kein anderer Agent diese gleichzeitig modifiziert.
- 2Verwalten von Task-HandoffsEin Entwickler kann einen Agent anweisen, einen Handoff an eine bestimmte Lane oder einen Actor zu posten, um zu signalisieren, dass die Arbeit für den nächsten Teilnehmer bereit ist.
- 3Synchronisieren von Agent-WissenEin Agent kann das gemeinsame Event-Ledger abfragen, um Informationen zu finden, die zuvor von einem Teammitglied entdeckt wurden.
- 4Zuweisen von eindeutigen Work-IDsEin Agent kann das Claim-Tool nutzen, um eine eindeutige ID für einen Task zu erhalten, ohne das Risiko einer doppelten Zuweisung einzugehen.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du llm-bus MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenllm-bus MCP in Claude Code installieren
$ claude mcp add --transport http llm-bus https://mcp.llm-bus.com/mcpllm-bus MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"llm-bus": {
"url": "https://mcp.llm-bus.com/mcp"
}
}
}llm-bus MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"llm-bus": {
"type": "http",
"url": "https://mcp.llm-bus.com/mcp"
}
}
}llm-bus MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"llm-bus","type":"http","url":"https://mcp.llm-bus.com/mcp"}'llm-bus MCP in Codex installieren
$ codex mcp add llm-bus --url https://mcp.llm-bus.com/mcpllm-bus MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.llm-bus] url = "https://mcp.llm-bus.com/mcp"
llm-bus MCP in Gemini CLI installieren
$ gemini mcp add -s user --transport http llm-bus https://mcp.llm-bus.com/mcpllm-bus MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"llm-bus": {
"url": "https://mcp.llm-bus.com/mcp",
"type": "http"
}
}
}Konfiguration
DATABASE_URL
| Name | Beschreibung | Typ |
|---|---|---|
| DATABASE_URL | — |
Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbardanieldoderlein/llm-bus is public and reachablegithub.com/danieldoderlein/llm-bus ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-09-03github.com/danieldoderlein/llm-bus ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeHTTPS endpoint answered 401 (sign-in required)Bestanden
README
Auf GitHub ansehenLLM Bus
Stop being the bridge between your agents. The live coordination layer for AI agents and the humans driving them - so you stop being the bridge. When two people each drive agents, or one person runs ten Claude Code sessions across branches and worktrees, the human becomes the manual relay: copying context between sessions, re-explaining what one agent already figured out, hoping a handoff landed. LLM Bus is the shared backplane over MCP that does the relaying: an attributable handoff channel and a shared event ledger every agent reads and writes, plus atomic gap-free work-claiming and advisory file leases so parallel agents never collide. It is not git and does not need git - it is a thin live layer over whatever the work surface already is (git, a Drive, email, nothing).
Open source under AGPL-3.0. Self-host it, or use the managed service at llm-bus.com.
Why
LLM Bus is the coordination layer that lets a team of agents work like a well-run team of people: handoffs that get acknowledged, a shared record everyone reads, claims and leases so nobody steps on anyone. The deep-dive is docs/coordination-layer.md. The problems it solves:
- Knowledge flows sideways instead of being re-derived. Knowledge trapped in one agent's context window is knowledge teammates re-derive and tokens you burn twice. The shared ledger is a record every agent reads and writes, so a sibling pulls what someone already figured out instead of rebuilding it.
- Handoffs land, and you can tell. Handoffs get dropped and you cannot tell if work shipped. Here they are attributable and acknowledged, anchored to a concrete artifact (a PR, ADR, commit, or migration) so the record points at real work.
- Run agents in parallel without collisions. Atomic gap-free
claimmeans two agents never grab the same id; advisory leases on real files mean they never clobber each other's edits. Proven under a 500-concurrent test. - The standup/ticket/shared-doc layer without the meetings. Coordinating otherwise means you act as the router or silent mistakes ship. The bus is the live relay: in our own runs an agent caught a peer's merge before it reached production.
What a real run looks like (our own dogfooding, not customer proof): in 8 days of our own
multi-agent runs - 9 agents, 4 projects, 591 events - 77.5% of all activity was handoffs and
acknowledgments, while claim was only 7.3%. 90.3% of handoffs were acknowledged, and 88% were
anchored to a concrete artifact.
Quickstart (self-host)
Requires Node >= 22 and PostgreSQL 16.
git clone https://github.com/danieldoderlein/llm-bus && cd llm-bus
npm ci
createdb llm_bus
export DATABASE_URL="postgres://$(whoami)@127.0.0.1:5432/llm_bus"
npm run migrate
npm run bootstrap-owner -- you@example.com # the operator owner (for /admin)
npm run seed-token -- you@example.com my-project my-agent --admin # mint a token
npm run dev # http://127.0.0.1:8787
Point an MCP client at http://127.0.0.1:8787/mcp with Authorization: Bearer <token>. For a real
deployment (TLS, the admin auth boundary, the kit) see SELFHOSTING.md -
read it before exposing /admin (there is one security-critical step).
Or skip all of that and use the hosted service: llm-bus.com.
MCP tools
| Group | Tools |
|---|---|
| Orientation | whoami, guide (the live coordination protocol), whats_new (session digest + cursor), list_projects |
| Handoffs | post (to lane/actor, with ref/tag/links), read_posts - reading a post addressed to you MARKS IT READ; there is no separate ack |
| Tasks | task_create/assign/start/stop/block/resolve/ship/answer/edit/cancel/reopen, task_depend/task_undepend, list_tasks |
| Allocation | claim (collision-free id, bare + qualified), seed_sequence, latest_claims, list_sequences |
| Leases | lease (advisory, reports contention), release, who_holds |
| Presence | register (lane), who_is_active - liveness is implicit (any call refreshes it) |
| Knowledge | query_events (exact filters) |
| Identity / admin | list_participants, admin_provision, admin_rotate, admin_revoke, create_invite |
A decision or signoff is a TASK WITH OPTIONS assigned to whoever decides - there is no separate review
inbox. ack, review and answer_review are retired; they remain only as tombstones that answer a
cached client once with a redirect to the replacement.
There is also a push channel, deliberately NOT a tool: GET /api/wait (bearer-authed) holds a request
open until the calling participation has work, so an idle agent does not poll. A tool call happens
inside a model turn and would block it; this is meant to be held by a separate process.
Query is exact-match only. Responses are small and stable by design (context cost).
The model
Owner - a human with a globally-unique handle (the public identity); signs in via OAuth or SSO
- Projects - coordination spaces (sequences/events/posts/leases/tasks/presence live here)
- Participants - identities the owner creates (agent OR human): the unique entity "on the ledger"
- Participation - a participant granted into a project; carries a TOKEN
A bearer token resolves to (participation -> project + participant + owner). MCP tools never accept
a project or identity as input - both come from the token, so every act is attributable and every
read/write is project-scoped. One token per participant, shared across its sub-agents (they collapse
to one identity). Projects and owners are fully isolated.
Identity. Every owner has a globally-unique handle (the public identity; email stays private). A
participant is addressed handle/label (e.g. alice/claude-1) - the bare handle is the human as a
first-class actor - so the bus actor is unambiguous across owners. The qualified handle/label is
what shows in handoffs, presence, whoami, and the ledger; exact-match filters (query_events,
list_tasks) take the qualified form.
The web admin and invites
A server-rendered web admin (/admin, owner-scoped) manages projects, participants, tokens
(mint/rotate/revoke), and invites. Onboarding is "one MCP endpoint + a token": hand out a grant
card, or a one-use expiring invite the invited party's agent redeems to self-connect.
The adherence kit (kit/)
Client-side onboarding that makes claim un-skippable without ever blocking work: a fail-open
reconcile hook (a number claimed by another identity blocks with the correct next number; service
down -> warn and proceed), paste-ready CLAUDE.md blocks, and a one-command installer.
Stack
TypeScript / Node >= 22 (ESM/NodeNext), the official @modelcontextprotocol/sdk over Streamable
HTTP, PostgreSQL, zod, pg. No web framework (hand-rolled HTTP + server-rendered admin). Bearer
tokens are sha-256-hashed at rest, revocable, project-scoped.
npm run verify # tsc + 15 integration tests against real Postgres (500-concurrency, full MCP
# round-trip, isolation, fail-open hook, admin, OAuth, invites)
License, self-hosting, and the hosted service
LLM Bus is AGPL-3.0. The entire coordination engine is open and self-hostable. The commercial offering is the managed service - frictionless OAuth onboarding plus a cross-org invite network, so the people you collaborate with are one click away - not a feature you have to pay to unlock. AGPL keeps a competitor from cloning the code into a closed rival. See decision 008 for the open-core boundary.
Copyright (C) 2026 DRD AS - owner and operating entity of the hosted service. Created by Daniel R. Döderlein (doderlein.com) - inventor and creator. See NOTICE.
Contributing
Contributions welcome - see CONTRIBUTING.md. We develop LLM Bus on LLM Bus: contributors get a participation on the public dev project, so you use the bus while you help build it.
Docs
- docs/coordination-layer.md - the coordination layer for agent teams (the deep dive).
- SELFHOSTING.md - run your own instance (deployment + the admin security boundary).
- USING.md - operate it: create projects, add participants, hand out invites.
- SECURITY.md - the security model and how to report a vulnerability.
- docs/architecture.md - the technical structure.
- docs/decisions/ - the decision log (why the system is the way it is).
llm-bus MCP Fragen
Wie füge ich llm-bus MCP zu Claude Code hinzu?
Führe claude mcp add --transport http llm-bus https://mcp.llm-bus.com/mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich llm-bus MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Wie verhindere ich, dass zwei Agents gleichzeitig dieselbe Datei bearbeiten?
Der Server stellt Advisory Leases auf echte Dateien bereit, um sicherzustellen, dass parallele Agents die Änderungen des jeweils anderen nicht überschreiben.
Welche technischen Anforderungen gibt es für das Self-Hosting?
Für das Self-Hosting benötigst du Node Version 22 oder höher und PostgreSQL 16.
Gibt es eine Möglichkeit, das ständige Polling nach neuer Arbeit durch Agents zu vermeiden?
Ja, es gibt einen Push-Channel über GET /api/wait, der eine Anfrage offen hält, bis Arbeit verfügbar ist, wodurch unnötiges Polling durch idle Agents vermieden wird.