Llm MCP Server

Connect Llm to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks. The llm mcp server is what makes that connection.

What the server does

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
• Handoffs land, and you can tell. — Handoffs get dropped and you cannot tell if work shipped. Here
• Run agents in parallel without collisions. — Atomic gap-free claim means two agents never grab
• The standup/ticket/shared-doc layer without the meetings. — Coordinating otherwise means you act

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

• Group — Tools
• Handoffs — post (to lane/participant, with ref/tag), read_posts, ack
• Knowledge — query_events (exact filters), whats_new (session digest + cursor)
• Allocation — claim (formatted, collision-free id), seed_sequence, latest_claims
• Leases — lease (advisory, reports contention), release, who_holds
• Tasks — task_create/assign/start/block/resolve/ship, list_tasks
• Presence — register (lane + status), who_is_active - liveness is implicit (any call refreshes it)

Credentials and setup notes

Configuration is passed through the environment: DATABASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

• Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Llm's toolset — Group, Handoffs, Knowledge and 4 more — is a fair guide to whether it matches your workflow. It is maintained by com.llm-bus; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.