llm-bus MCP server
Commit Sep 3, 2026Coordinates multiple AI agents through a shared event ledger, atomic task claims, and advisory file leases to prevent collisions and manage handoffs.
Also known as danieldoderlein/llm-bus
- Stars
- 9
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Sep 3, 2026
- License
- AGPL-3.0
What is llm-bus MCP?
llm-bus coordinates multiple AI agents through a shared event ledger, atomic task claims, and advisory file leases to prevent collisions and manage handoffs.
Summary generated from the project's README
About llm-bus MCP server
LLM Bus acts as a coordination layer for multiple AI agents and human operators to prevent work collisions and manage handoffs. It functions as a shared backplane over the Model Context Protocol, providing a live event ledger that all participants can read and write. This system allows agents to share knowledge sideways rather than re-deriving information, saving tokens and time. Users can self-host the server using Node.js and PostgreSQL or utilize a managed service.
Developers interact with the server through specific MCP tools categorized into groups like Orientation, Handoffs, Tasks, and Leases. The system uses atomic gap-free claims to ensure two agents never grab the same task ID, and advisory file leases to prevent agents from clobbering each other's edits. Access is managed via bearer tokens that are project-scoped and attributable to specific participants. This setup enables parallel agent workflows across different worktrees or branches without requiring manual context copying by a human.
What you can do with it
- 1Preventing parallel edit collisionsAn agent can request an advisory lease on a file to ensure no other agent modifies it simultaneously.
- 2Managing task handoffsA developer can instruct an agent to post a handoff to a specific lane or actor to signal that work is ready for the next participant.
- 3Synchronizing agent knowledgeAn agent can query the shared event ledger to find information previously discovered by a teammate.
- 4Allocating unique work IDsAn agent can use the claim tool to grab a unique identifier for a task without risking a duplicate assignment.
Written from the project's README. Every use case is checked against a quote from it.
How to install llm-bus MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall llm-bus MCP in Claude Code
$ claude mcp add --transport http llm-bus https://mcp.llm-bus.com/mcpInstall llm-bus MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"llm-bus": {
"url": "https://mcp.llm-bus.com/mcp"
}
}
}Install llm-bus MCP in VS Code
.vscode/mcp.json
{
"servers": {
"llm-bus": {
"type": "http",
"url": "https://mcp.llm-bus.com/mcp"
}
}
}Install llm-bus MCP in VS Code CLI
$ code --add-mcp '{"name":"llm-bus","type":"http","url":"https://mcp.llm-bus.com/mcp"}'Install llm-bus MCP in Codex
$ codex mcp add llm-bus --url https://mcp.llm-bus.com/mcpInstall llm-bus MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.llm-bus] url = "https://mcp.llm-bus.com/mcp"
Install llm-bus MCP in Gemini CLI
$ gemini mcp add -s user --transport http llm-bus https://mcp.llm-bus.com/mcpInstall llm-bus MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"llm-bus": {
"url": "https://mcp.llm-bus.com/mcp",
"type": "http"
}
}
}Configuration
DATABASE_URL
| Name | Description | |
|---|---|---|
| DATABASE_URL | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabledanieldoderlein/llm-bus is public and reachablegithub.com/danieldoderlein/llm-bus ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-03github.com/danieldoderlein/llm-bus ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubLLM 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 questions
How do I add llm-bus MCP to Claude Code?
Run claude mcp add --transport http llm-bus https://mcp.llm-bus.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add llm-bus MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I prevent two agents from editing the same file at once?
The server provides advisory leases on real files to ensure parallel agents do not clobber each other's edits.
What are the technical requirements for self-hosting?
To self-host, you require Node version 22 or higher and PostgreSQL 16.
Is there a way to avoid agents constantly polling for new work?
Yes, there is a push channel via GET /api/wait that holds a request open until work is available, preventing idle agents from polling.