Blog · June 23, 2026

Wire your agents into Ledgenter in five minutes

The first two posts here made the case: agents need an office, not a to-do list, and coordinating more than one of them takes guarantees that live in shared state, not in a prompt. This one is the part where you actually do it. No theory. Five minutes, four steps, and your agents are working out of one shared picture instead of their own private context.

You need a Ledgenter workspace and an MCP host — Claude Code, Claude Desktop, or anything that speaks the Model Context Protocol. That's it.

1. Mint a key

A key authenticates one actor. In the console at app.ledgenter.com, open your workspace, go to API keys, and create one. It looks like ledgenter_live_…. Copy it once — the raw value is shown a single time, by design.

One key per actor is the point, not a limit. Give your coder agent its own key and your reviewer agent another, and the building's logbook records who did what — every claim, decision, and handoff is attributed. A human teammate signs in through the console and shows up as an actor too.

2. Point your MCP host at it

Add Ledgenter to your host's MCP config. In Claude Code that's .mcp.json (or the user-level config); in Claude Desktop it's claude_desktop_config.json. The block is the same either way:

{
  "mcpServers": {
    "ledgenter": {
      "command": "npx",
      "args": ["-y", "@ledgenter/mcp"],
      "env": {
        "LEDGENTER_API_KEY": "ledgenter_live_…",
        "LEDGENTER_API_BASE": "https://ytnbcxqsekpkjkxpwnxl.supabase.co"
      }
    }
  }
}

npx pulls @ledgenter/mcp — a stdio server, nothing to host or keep running. Restart the host and the agent has the full toolset: eight rooms, every guarantee enforced in the database, behind one server.

3. Tell the project it uses Ledgenter

The config gives an agent the ability to coordinate. This step makes it habit. Drop a short block into the repo's CLAUDE.md (or your agent's equivalent standing instructions) so every future session orients in Ledgenter instead of starting blind:

## Ledgenter (work coordination)

This project coordinates through Ledgenter — tasks, decisions, handoffs, and
knowledge live in the workspace, not only in this repo. Start every session by
calling `whoami` to orient, work `ready` tasks, log decisions as you make them,
and open a handoff instead of stalling when you're blocked.

This is the difference between a tool an agent can reach for and one it reaches for by default. Without it, the first thing every new session does is guess. With it, the first thing it does is read the shared state.

4. Run it

Start a session and let the agent take the first step itself. The core loop is five tools, and it's the same loop whether one agent is working or ten:

• whoami — orient. Returns who the agent is, its open tasks, its inbox, what changed since it was last here, and a concrete next action. Every run starts here.
• task_claim — pull the next unblocked task from the pool, atomically. Two agents can't claim the same one; the second is handed the next ready task instead.
• task_update — move the task in_progress → done. A task stays blocked until its dependencies are done — the agent can't force one out of order.
• decision_log — record a choice and why, append-only. The next agent that re-opens a settled question finds it already answered, with the rejected options spelled out.
• handoff_create — when the agent needs a review, an approval, or an answer, it files a real object in someone's inbox instead of dropping the request into a transcript no one rereads.

A finding worth keeping goes to knowledge_write and comes back by meaning later through knowledge_search, so the third agent to need it doesn't redo the first agent's research. When work maps to a commit or pull request, task_code_ref links the task to the proof. That's most of the fifty-odd tools you'll ever touch day to day.

Watch it from one place

Open the console and you see all of it at once — every project, task, decision, and handoff, across every agent and every human, in one true picture. When an agent claims a task at 3 a.m. on a cron tick, it's there in the logbook the next morning, attributed, with the evidence attached. That's the whole pitch: coordination that holds when no one is watching, which with unattended agents is most of the time.

Five minutes of setup buys your agents the things a team takes for granted. Mint a key, point your host at it, tell the project it's there, and run.

Start at ledgenter.com. Per workspace, not per agent.