VibeHard MCP Server.

Setup

curl -fsSL https://vibehard.ai/download/install-agent.sh | bash

Then add the server to your agent’s MCP config, or let the installer register it:

{
  "mcpServers": {
    "vibehard-agent": {
      "command": "/Users/you/.local/bin/vibehard-agent",
      "args": ["mcp"]
    }
  }
}

Use the absolute path the installer prints (for example /Users/you/.local/bin/vibehard-agent on a Mac or /home/you/.local/bin/vibehard-agent on Linux); MCP clients do not expand ~. The installer writes this same entry, named vibehard-agent, when you agree at the prompt or pass --mcp-register.

It runs over standard input and output on your machine. No API key is needed for the Community Edition.

Tools exposed (16)

• — vibehard_session_open / vibehard_session_close: Open and close a session with the factory.
• — vibehard_build_start: Submit a software request. The factory runs the pipeline and hands the reasoning steps to your agent as work orders.
• — vibehard_workflow_brief: Prepare a workflow brief or evidence bundle locally on your machine. Hosted workflows are coming soon.
• — vibehard_task_next / vibehard_task_submit: Fetch the next work order and return your agent’s result; the pipeline resumes.
• — vibehard_review_next / vibehard_review_respond: See the next open human checkpoint and record the answer.
• — vibehard_status / vibehard_progress: Check a job’s status, or get a plain-English progress report.
• — vibehard_gate: Run the verification chain on a folder as a background job.
• — vibehard_deploy: Run the chain and, only if it passes, write the sealed pass marker.
• — vibehard_snapshot / vibehard_rollback: Take a labeled snapshot, or roll the workspace back to one. A safety snapshot is taken first, and untracked files are set aside, not deleted. Rollback needs a target and a reason, is limited to two per job, and may use one repair attempt.
• — vibehard_handoff: Generate the handoff package for a finished job: the as-built report and a maintainer runbook.
• — vibehard_install_info: Get install instructions and download details for your edition and platform.

Under the hood

• — Your agent does all the reasoning. The factory issues work orders and checks every result, and a network guard in the daemon blocks calls to AI model providers.
• — Results are checked by the 44-gate chain. Only a full pass writes the sealed pass marker, which is bound to the project files and to the set of gates that ran.
• — Human checkpoints (questions, scope review, plan approval) are recorded. On the strictest setting, sensitive questions must be answered by a person.

Full documentation

Documentation · llms.txt for agents.