Agentic Control Framework MCP Server

Connect Agentic Control Framework to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP-compliant agentic control framework with 80+ tools for Claude Code and autonomous agent development. The agentic control framework mcp server is what makes that connection.

What the server does

AI‑native orchestration layer (CLI + MCP) with 80+ tools for context engineering—retrieval, code editing, browser automation, terminal orchestration, and persistent memory—designed for Claude Code, Cursor, Codex, and VS Code. This README reflects the current code and tested integrations.

Available tools

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

• update — subtask, bump, defer, prioritize, deprioritize
• recalculate — priorities, priority-stats, dependency-analysis
• start-file — watcher, stop-file-watcher, file-watcher-status, force-sync
• list — templates, suggest-template, calculate-priority, add-with-template
• execute_command — Run shell commands with timeout
• read_output — Read from running processes
• force_terminate — Kill processes
• list_sessions — Show active terminal sessions
• list_processes — Show running processes
• kill_process — Terminate processes
• browser_navigate — Navigate to URLs
• browser_navigate_back — Go back

Credentials and setup notes

Configuration is passed through the environment: ACF_PATH, WORKSPACE_ROOT, GEMINI_API_KEY. 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.

## Installation

The server ships on npm as `playwright`, 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 browser automation 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. Agentic Control Framework's toolset — `update`, `recalculate`, `start-file` and 11 more — is a fair guide to whether it matches your workflow. It is maintained by FutureAtoms; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.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.
- With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agentic Control Framework.
- 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.