Agentpack MCP Server

Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.

Local serverstdio

What is the Agentpack MCP server?

Connect Agentpack to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP. The agentpack mcp server is what makes that connection.

What the server does

Here it is live. Session 1: Claude Code investigates a flaky test and records what it learns through the Agentpack MCP tools. Session 2, next day, empty context: the agent loads the task state and picks up exactly where the first session stopped — no re-investigation:

Available tools

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

  • Local — first.** Plain files in your repo. No cloud, no telemetry, no network calls
  • Agent — oriented.** A local MCP server plus generated project instructions (AGENTS.md, CLAUDE.md, Cursor rules) tell agents when to load and record state
  • Human — friendly.** The same state is available through the CLI for inspection, debugging, and manual handoff
  • Best — effort redaction of secret-looking values in stored context and handoff output

Installation

The server ships on npm as agentpack-cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Where it fits

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agentpack's toolset — Local, Agent, Human and 1 more — is a fair guide to whether it matches your workflow. It is maintained by ihorponom; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Localfirst.** Plain files in your repo. No cloud, no telemetry, no network calls.
Agentoriented.** A local MCP server plus generated project instructions (AGENTS.md, CLAUDE.md, Cursor rules) tell agents when to load and record state.
Humanfriendly.** The same state is available through the CLI for inspection, debugging, and manual handoff.
Besteffort redaction of secret-looking values in stored context and handoff output.

How to install the Agentpack MCP server

{
  "mcpServers": {
    "agentpack": {
      "command": "npx",
      "args": ["-y", "agentpack-cli"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Agentpack to Local.
  • Use Agentpack to Agent.
  • Use Agentpack to Human.

Frequently asked questions

It connects Agentpack to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Local, Agent, Human, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentpack directly.