Fullrun

io.github.tuckerschreiberPublished by GitHub account tuckerschreiberv0.1.1Updated Nov 3, 2026

Google Ads management for AI agents — diagnose, optimize, and manage campaigns.

VerifiedSTDIODesktop onlyProductivity & WorkflowBusiness & Commerce

Overview

AI-generated overview

Lets an assistant diagnose and optimize Google Ads accounts through the Fullrun API: health triage, campaign and keyword inspection, and AI-driven fixes.

What you can do
  • Run a prioritized account health triage (critical to low) and re-run it to confirm fixes
  • List campaigns with status, budget and metrics, and list keywords with performance data
  • Read account performance metrics such as clicks, conversions and CPA over a look-back window
  • Trigger a full AI-powered optimization run that adjusts bids, adds ad extensions, pauses wasteful keywords and creates campaigns
  • Return colored terminal output or structured JSON when piped to another program
When to use it
Useful when an assistant should monitor and improve Google Ads accounts — finding underperforming campaigns or keywords, reviewing spend and conversion metrics, and applying automated optimizations without leaving the chat.
Requirements
Runs as a local process via npx or a global npm install, so Node.js is needed. Requires a Fullrun account with a connected Google Ads account and a Fullrun API key supplied in the FULLRUN_API_KEY environment variable. Network access to the Fullrun API is required.
Before you install
The optimization run changes live ad accounts: it adjusts bids, pauses keywords and creates campaigns, so spending and campaign structure can change. All Google Ads access is delegated to the Fullrun service, which holds the Google Ads connection; the API key is a credential for that service. Guardrails such as bid caps and budget limits are enforced server-side, not by the client.

Installation

In SourceWeft

  1. Open Fullrun in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[Fullrun]

Google Ads management CLI for AI agents.
Works with OpenClaw, Claude, and any agent that can run shell commands.

Fullrun is an AI agent that manages Google Ads for you. It monitors your campaigns around the clock, diagnoses problems, adjusts bids, adds missing ad extensions, pauses wasteful keywords, and creates new campaigns — all autonomously.

This CLI brings that same engine to your terminal. Instead of using the Fullrun dashboard, you (or your AI agent) can manage Google Ads with simple commands. Every command auto-detects your environment — colored output in a terminal, structured JSON when piped to another program.

bash
npm install -g fullrunfullrun login frun_YOUR_API_KEYfullrun triage

What an agent can do

  1. Diagnose — Run fullrun triage to get a prioritized health report (CRITICAL → HIGH → MEDIUM → LOW)
  2. Inspect — List campaigns, keywords, and performance metrics
  3. Optimize — Trigger fullrun run to let the AI agent fix the highest-priority issues
  4. Repeat — Triage again to confirm the fixes worked

All the hard stuff — Google Ads API calls, bid calculations, budget guardrails, PPC best practices — happens server-side. The CLI is a thin client. No credentials stored on your machine.

Commands

CommandDescription
fullrun login <key>Authenticate with your API key
fullrun triageAccount health report with prioritized issues
fullrun campaigns:listList campaigns with status, budget, and metrics
fullrun performanceAccount metrics — clicks, conversions, CPA
fullrun keywords:listKeywords with performance data
fullrun runTrigger a full AI-powered optimization run

Options

  • --format json — Force JSON output (default when piped)
  • --format human — Force colored terminal output (default in TTY)
  • --days <n> — Look-back period for performance data (default 7, max 90)
  • --campaign <id> — Filter keywords by campaign

Agent integration

OpenClaw

Install the CLI globally and OpenClaw auto-discovers it via the bundled SKILL.md:

bash
npm install -g fullrun

Then tell your agent: "Check my Google Ads and fix anything that's underperforming."

Claude Code

The SKILL.md works as a Claude Code skill. The agent reads it and knows how to use every command.

MCP (Claude Desktop / Cursor)

json
{  "mcpServers": {    "fullrun": {      "command": "npx",      "args": ["@fullrun/mcp"],      "env": {        "FULLRUN_API_KEY": "frun_..."      }    }  }}

Any agent

Any agent that can execute shell commands can use Fullrun. Output is auto-detected — JSON when piped, human-readable in a terminal.

Getting an API key

  1. Sign up at fullrun.app
  2. Connect your Google Ads account
  3. Go to Settings > API Keys
  4. Create a key and copy it

How it works

CLI / MCP / Agent      │      ▼  Fullrun API (api key auth)      │      ▼  Triage engine → Google Ads API  Guardrails, bid caps, PPC rules

The CLI never touches Google Ads directly. It calls the Fullrun API, which runs the same triage and optimization engine that powers the web dashboard. All guardrails (mutation limits, bid caps, budget safety) are enforced server-side.

Development

bash
git clone https://github.com/tuckerschreiber/fullrun-clicd fullrun-clinpm installnpx tsx src/bin/fullrun.ts --help

License

MIT

Source: README.md at commit 8fcd916

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts