mureo

Website · 日本語

mureo — your local-first AI ad ops crew. Find waste, audit changes, run ad accounts safely.

Local-first. Strategy-grounded. Safety-gated.

Works with Claude Code, Cursor, Codex & Gemini. mureo sits on top of the official ad-platform MCPs and gives your AI a strategy to follow, an outcome to be measured against, and an audit trail you can show to anyone — credentials never leave your machine.

Real output: brand cannibalization auto-detected on a 30-day BYOD bundle (anonymized B2B SaaS account). More samples ↓

What is mureo?

mureo is a local-first control plane for AI ad ops. Once installed, AI agents (Claude Code, Cursor, Codex, Gemini, etc.) operate Google Ads, Meta Ads, Search Console, and GA4 through mureo — which keeps every action grounded in your business strategy, tied to real outcomes, and recorded in an audit log you can replay.

When official ad-platform MCPs ship (Meta Ads MCP, Google Ads MCP, etc.), mureo uses them as drivers. mureo's value is not the API connection — it is what happens around it:

• Strategy-grounded — every decision reads STRATEGY.md (persona, USP, brand voice, goals)
• Safety-gated — rollback allow-list, GAQL guards, BYOD read-only by default, credential guard, per-platform throttle
• Cross-platform — Google Ads / Meta Ads / Search Console / GA4 in one workflow
• Auditable — append-only action log with rollback
• Local-first — credentials never leave your machine
• Learnable — /learn builds account-specific knowledge over time

Choose your setup

The easy way: pip install + mureo configure

For most people, two commands set up mureo for Claude — no terminal secret-pasting, no JSON editing:

pip install mureo
mureo configure

mureo configure opens a local browser UI (bound to 127.0.0.1, ephemeral port — no remote access) that walks you through everything:

• Pick your Claude app — Claude Code (CLI / Desktop app) or Claude Desktop app (Chat, Cowork); mureo writes the right config file for that host.
• Basic setup — registers the mureo MCP server, the credential-guard hook (Claude Code), and the workflow skills, in one click.
• Connect platforms — interactive Google / Meta OAuth in the browser (deep links to each console), or paste a GA4 service-account path / project id; values are written to ~/.mureo/credentials.json for you.
• Official MCP providers — register Google Ads / GA4 official MCPs into ~/.claude.json. (Meta is a hosted MCP with no OAuth dynamic client registration, so it can't be wired as a Claude Code user-scope server; the UI shows how to add it as a Claude.ai account connector instead — it then works in Claude Code and Claude Desktop alike.)
• Per-platform tool source — a dashboard toggle to switch each platform between mureo-native tools and the official MCP.
• Demo / BYOD — scaffold a demo scenario or import your XLSX bundle from the same UI.

The terminal flow below still works (and is scriptable); mureo configure is just the friendlier front door to the same operations.

Manual / scriptable (3 modes × 3 hosts)

mureo has 3 modes (where the data comes from) and runs across 3 hosts (where the agent operates). Pick the cell, run the command — or just use mureo configure above:

Full per-row walkthroughs (including how to obtain your XLSX, where to put it, and how to import it): Getting Started →.

Not familiar with Google Cloud Console or Meta for Developers? OAuth flows, developer-token registration, and Business-app sign-ups can feel intimidating if you have never used those consoles before. Start with BYOD — you will see what mureo can do for your account in a few minutes, then decide whether the Live API path is worth setting up.

BYOD vs Live API at a glance

Mode A: BYOD — 5 minutes to first diagnosis, no OAuth

Drop a Sheet-bundle XLSX into mureo and get a strategy-grounded multi-platform diagnosis. No OAuth flow, no developer-token approval, no SaaS sign-up.

pip install mureo
mureo setup claude-code --skip-auth
mureo byod import ~/Downloads/mureo-google-ads.xlsx
mureo byod import ~/Downloads/mureo-meta-ads.xlsx     # add Meta later — they're independent
# Open Claude Code and ask: "Run /daily-check"

Producing the XLSX is a one-time setup per platform:

• Google Ads — Apps Script template populates a Google Sheet you own; download as XLSX (~5 min). See guide →
• Meta Ads — Saved Report in Ads Manager → 2-click export. Recognized in 9 languages (English / 日本語 / 简体中文 / 繁體中文 / 한국어 / Español / Português / Deutsch / Français), so you do not need to switch Ads Manager UI to English. See guide →

Read-only by construction. Every mutation tool (/rescue, /budget-rebalance, /creative-refresh) returns {"status": "skipped_in_byod_readonly"} — the agent analyzes and recommends but never writes to your real account. Upgrade a platform to the Live API later with mureo byod remove --google-ads (one platform) or mureo byod clear (all).

Mode B: Live API OAuth — full functionality

Connect mureo directly to Google Ads / Meta Ads APIs. Required to actually execute changes (/rescue, /budget-rebalance, /creative-refresh, mureo rollback apply) and for GA4 / Search Console support.

pip install mureo
mureo configure            # browser UI: pick host, basic setup, OAuth, providers
# …or the terminal equivalent:
#   mureo auth setup        # interactive OAuth in the terminal
#   mureo setup claude-code # MCP server + workflow skills
# Open Claude Code and ask: "Run /daily-check"

Prerequisites: Google Ads Developer Token + OAuth Client; Meta App ID + Secret. Both mureo configure (browser) and mureo auth setup (terminal) walk you through them — see Authentication below.

Which mode fits?

Recommended starting path: Try Mode A on one platform first → run /daily-check → decide whether to add the second platform via BYOD or graduate to Mode B. The presence of ~/.mureo/byod/manifest.json is the switch — no config flags, no global toggle.

See docs/byod.md for the full walkthrough, Saved Report config, and per-platform export instructions.

Features

Strategy-driven decisions

Every operation starts from STRATEGY.md -- your persona, USP, brand voice, goals, and operation mode. The agent doesn't just optimize metrics; it optimizes toward your business objectives.

/creative-refresh reads your Persona and USP before drafting a single headline.
/budget-rebalance checks your Operation Mode before shifting a single dollar.
/rescue cross-references your Goals before recommending what to fix first.

Cross-platform analysis

mureo orchestrates across Google Ads, Meta Ads, Search Console, and GA4 in a single workflow:

• /daily-check -- pulls delivery status, ad performance, organic search trends, and site behavior across all platforms, then correlates them into one health report.
• /search-term-cleanup -- compares paid keywords against organic rankings to eliminate wasteful overlap.
• /competitive-scan -- combines auction insights with organic position data for a complete competitive picture.

The agent auto-discovers your configured platforms. Add Meta Ads later? Every command adapts automatically.

Built-in marketing expertise

Campaign diagnostics that pinpoint why ads aren't delivering -- budget constraints, bidding misconfiguration, policy disapprovals, and more. Search term intent classification. Budget efficiency scoring. RSA ad validation and asset auditing. Landing page analysis. Device-level CPA gap detection. The kind of knowledge experienced ad operators carry in their heads -- built into every workflow.

Learnable operational know-how

When you correct the agent or share an operational insight, /learn saves it to a persistent knowledge base. That knowledge is loaded at the start of every future session, so the agent doesn't repeat the same mistakes and applies what it learned to similar situations across your account.

You: "That's not a real CPA spike -- this industry always dips in Golden Week."
Agent: Saved. I'll flag this as seasonal next time.

→ Written to the diagnostic knowledge base.
→ Every future /daily-check and /rescue will factor this in.

Beyond your own /learn history, mureo can also consult external advisor MCP servers — consulting firms, industry trade groups, OSS communities, or internal team wikis can stand up a vector-search MCP server that holds practitioner know-how (platform quirks, industry CPA / CTR benchmarks, post-cutoff platform updates) the LLM does not carry. Configure them in ~/.mureo/insight_sources.json and the agent calls mureo_consult_advisor from any diagnostic skill to pull the matching fragments. The advisor keeps the corpus; mureo passes a context-rich query and receives only the top-k snippets. See docs/insight-federation.md for the operator setup and the server-author spec.

Security by design

Marketing accounts are a high-value target. mureo is built with defense-in-depth for AI-driven operations:

• Credential guard — mureo setup claude-code installs a PreToolUse hook that blocks AI agents from reading ~/.mureo/credentials.json, .env, and similar secrets, so a prompt-injection payload cannot exfiltrate tokens via the file-system tools.
• GAQL input validation — every ID, date, date-range constant, and string literal that enters a Google Ads query flows through one whitelist-based surface (mureo/google_ads/_gaql_validator.py), and BETWEEN clauses pattern-match and revalidate their dates instead of passing raw caller input into GAQL.
• Anomaly detection — mureo/analysis/anomaly_detector.py compares current campaign metrics against a median-based baseline from the action log and emits prioritized alerts for zero spend, CPA spikes, and CTR drops, with sample-size gates that suppress single-day noise. Exposed to agents via the analysis_anomalies_check MCP tool; state_file is sandboxed inside the MCP server's CWD so a prompt-injected agent cannot redirect it at an attacker-crafted STATE.json.
• Rollback with allow-list gating — mureo/rollback/ turns agent-authored reversible_params hints into concrete RollbackPlan records. Only operations on an explicit allow-list are planned; destructive verbs (.delete, .remove, .transfer) and unexpected parameter keys are refused, so a compromised agent cannot smuggle a privileged call through the rollback path. mureo rollback list / show let operators preview plans, and the rollback_apply MCP tool executes them by re-dispatching through the same handler used for forward actions so the reversal re-enters the full policy gate (auth, rate limit, validation). Apply requires confirm=true (literal boolean), refuses rollback.* self-recursion, records the reversal as an append-only action_log entry tagged with rollback_of=<index>, and refuses a second apply of the same index.
• Immutable data models — every state object (StateDocument, ActionLogEntry, CampaignSnapshot, Anomaly, RollbackPlan) is a frozen=True dataclass; an agent cannot silently mutate its own record of what happened.
• Local-only credentials — tokens are loaded from ~/.mureo/credentials.json or environment variables and transmitted only to the official ad-platform APIs. mureo itself has no telemetry.

See SECURITY.md for the full threat model and vulnerability reporting process.

Workflow Commands

Getting started

pip install mureo
mureo setup claude-code

# Then in Claude Code:
/onboard          # First time: set up strategy + state
/daily-check      # Daily: check all campaigns
/rescue           # When performance drops

Example: /creative-refresh in action

You: /creative-refresh

Agent reads STRATEGY.md:
  Persona: "Budget-constrained SaaS marketer"
  USP: "AI reduces ad ops workload by 10h/week"
  Brand Voice: "Data-driven, no hype"

Agent discovers platforms from STATE.json:
  → Google Ads + Meta Ads configured

Agent pulls data across platforms and data sources:
  → Creative audit         → 3 underperforming Google Ads assets
  → Landing page analysis  → LP highlights: free trial, ROI improvement
  → Search Console         → "ad automation" has strong organic clicks
  → GA4                    → high bounce rate on pricing page

Agent generates platform-appropriate copy from your strategy:
  Google Ads: "Cut Ad Ops Time by 60% with AI"  ← Persona pain point
  Google Ads: "Free Trial | Ad Automation"       ← LP + organic keyword
  Meta Ads:   "Stop drowning in ad reports..."   ← Brand Voice + social format

Agent validates, then asks for approval:
  "I suggest replacing 3 Google Ads headlines and 2 Meta ads. Here's why..."

You approve → Agent updates each platform.

What the output actually looks like (anonymized B2B SaaS account)

Real diagnostic excerpts from a 30-day BYOD bundle on a Japanese B2B SaaS account. Campaign / ad-group names are anonymized and brand search terms replaced with <brand>. Numbers are unchanged so the math holds.

/search-term-cleanup — brand cannibalization detected automatically

Why this matters: numbers-only tools dedupe by recency. mureo reads STRATEGY.md, notices the two campaigns have different intents (brand vs generic lead-gen), and routes the term to where it converts — a 7× CPA gap that nobody was acting on.

/daily-check — Meta CV-definition mismatch caught at the source

Why this matters: link_click vs pixel_lead optimization is a tracking distinction that doesn't show on a numbers-only dashboard. mureo surfaces result_indicator per campaign so the agent compares apples to apples before recommending a budget move.

Analysis & domain knowledge (built-in)

Quick Start

Prerequisites

• Google Ads -- Developer Token and OAuth Client ID / Client Secret
• Meta Ads -- Create an app on Meta for Developers to obtain an App ID / App Secret (development mode is fine)

Both mureo configure (browser) and mureo auth setup (terminal) walk you through both.

Browser configuration UI (mureo configure)

mureo auth setup --web was removed — its browser flow is now part of the unified mureo configure UI.

Pasting long secrets into a terminal prompt is error-prone. mureo configure starts a short-lived local UI on http://127.0.0.1:<random-port>/ and opens your browser. Beyond credential entry it covers the whole Claude setup:

• choose the Claude host (Claude Code / Claude Desktop) — mureo writes that host's config file;
• one-click basic setup (mureo MCP server + credential-guard hook + workflow skills);
• connect platforms — interactive Google / Meta OAuth in the same window (each field deep-links to Google Cloud Console / Google Ads API Center / Meta for Developers), or a GA4 service-account path / project id; written to ~/.mureo/credentials.json;
• register the official MCP providers (Google Ads / GA4) into ~/.claude.json; Meta is a hosted MCP with no OAuth dynamic client registration, so the UI shows how to add it as a Claude.ai account connector (works in Claude Code and Claude Desktop) instead of registering it locally;
• a dashboard to review status, switch each platform between mureo-native and the official MCP, and scaffold Demo / BYOD.

Flags: --no-browser (don't auto-open a tab), --timeout-seconds N (idle shutdown, default 600).

Claude Code (recommended)

pip install mureo
mureo setup claude-code

This single command handles everything:

1. Google Ads / Meta Ads authentication (OAuth)
2. MCP server configuration for Claude Code
3. Credential guard (blocks AI agents from reading secrets)
4. Workflow commands (/daily-check, /rescue, /learn, etc.)
5. Skills (tool references, strategy guide, evidence-based decisions, diagnostic knowledge)

After setup, run /onboard in Claude Code to get started.

Cursor

pip install mureo
mureo setup cursor

Cursor supports MCP tools but does not support workflow commands or skills.

Codex CLI

pip install mureo
mureo setup codex

Full parity with Claude Code: MCP server, credential guard (PreToolUse hook), workflow commands, and skills are all installed under ~/.codex/. Workflow commands are installed as Codex skills at ~/.codex/skills/<command>/SKILL.md (Codex CLI 0.117.0+ no longer surfaces ~/.codex/prompts/, see openai/codex#15941); invoke them with $daily-check or the /skills picker.

Gemini CLI

pip install mureo
mureo setup gemini

Registers mureo as a Gemini CLI extension at ~/.gemini/extensions/mureo/ with MCP server config and CONTEXT.md as the context file. Gemini CLI does not support PreToolUse hooks or the .md command format mureo bundles, so those layers are not installed.

CLI only (authentication management)

pip install mureo
mureo auth setup
mureo auth status

Docker

Run the mureo MCP server in an isolated container. Useful for:

• Non–Claude Code MCP clients: Cursor, Codex CLI, Gemini CLI, Continue, Cline, Zed, or any custom MCP client.
• CI/CD pipelines: scheduled anomaly checks, rollback dry-runs, weekly reports.
• Multi-tenant / agency ops: isolated credentials per client via separate containers.
• MCP registry health checks (Glama, etc.).

Slash commands (/daily-check, /rescue) and the credential-guard hook are Claude Code–specific UX. For those, use pip install mureo with mureo setup claude-code instead.

Build and run

docker build -t mureo .
docker run --rm -v ~/.mureo:/home/mureo/.mureo mureo

Connect your MCP client by pointing its config at this docker run command.

Authentication

Credentials are loaded from /home/mureo/.mureo/credentials.json inside the container (via bind mount) or from environment variables. Three common patterns:

1. Mounted credentials file — if ~/.mureo/credentials.json already exists on the host (from a prior mureo auth setup, a team-shared vault, or hand-crafted), the bind mount above is enough.

Schema for hand-crafting:

{
  "google_ads": {
    "developer_token": "...",
    "client_id": "...apps.googleusercontent.com",
    "client_secret": "...",
    "refresh_token": "...",
    "login_customer_id": "1234567890"
  },
  "meta_ads": { "access_token": "..." }
}

Required: Google needs developer_token / client_id / client_secret / refresh_token. Meta needs access_token. Search Console reuses the Google OAuth credentials (OAuth app must include the https://www.googleapis.com/auth/webmasters scope).

2. Environment variables — useful for CI/CD where secrets come from a secret manager:

docker run --rm \
  -e GOOGLE_ADS_DEVELOPER_TOKEN=... \
  -e GOOGLE_ADS_CLIENT_ID=... \
  -e GOOGLE_ADS_CLIENT_SECRET=... \
  -e GOOGLE_ADS_REFRESH_TOKEN=... \
  -e GOOGLE_ADS_LOGIN_CUSTOMER_ID=... \
  -e META_ADS_ACCESS_TOKEN=... \
  mureo

Supported: GOOGLE_ADS_{DEVELOPER_TOKEN, CLIENT_ID, CLIENT_SECRET, REFRESH_TOKEN, LOGIN_CUSTOMER_ID, CUSTOMER_ID}, META_ADS_{ACCESS_TOKEN, APP_ID, APP_SECRET, TOKEN_OBTAINED_AT, ACCOUNT_ID}.

3. Interactive wizard inside Docker — if you don't have OAuth tokens yet and don't want to install mureo on the host:

docker run -it --rm -v ~/.mureo:/home/mureo/.mureo mureo mureo auth setup

Walks you through the OAuth flow in the terminal and writes credentials.json to the mounted volume. Subsequent runs pick it up automatically (pattern 1).

To obtain OAuth tokens outside mureo:

• Google Ads OAuth 2.0 refresh token: https://developers.google.com/google-ads/api/docs/oauth/overview
• Meta long-lived access token: https://developers.facebook.com/docs/facebook-login/guides/access-tokens/get-long-lived

What gets installed

Skills reference

Connecting GA4 (Google Analytics 4)

mureo's workflow commands can leverage GA4 data (conversion rates, user behavior, landing page performance) when a GA4 MCP server is configured alongside mureo. GA4 data is optional — all commands work without it.

Setup using Google Analytics MCP:

1. Enable the required APIs in your GCP project:

   • Google Analytics Admin API -- click "Enable"
   • Google Analytics Data API -- click "Enable"

2. Install and authenticate:

   hljs language-bash

   Copy

   pipx install analytics-mcp
   
   gcloud auth application-default login \
     --scopes https://www.googleapis.com/auth/analytics.readonly,https://www.googleapis.com/auth/cloud-platform
   

3. Add to ~/.claude/settings.json alongside mureo:

   hljs language-json

   Copy

   {
     "mcpServers": {
       "mureo": {
         "command": "python",
         "args": ["-m", "mureo.mcp"]
       },
       "analytics-mcp": {
         "command": "pipx",
         "args": ["run", "analytics-mcp"],
         "env": {
           "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/application_default_credentials.json",
           "GOOGLE_PROJECT_ID": "your-gcp-project-id"
         }
       }
     }
   }
   

Connecting Other MCP Servers

mureo works alongside any MCP server in the same client session. Add them to your settings and workflow commands will incorporate their data when available. See docs/integrations.md for details.

Writing your own provider plugin

mureo's provider abstraction lets any pip-installable package add a new ad-platform provider (Microsoft/Bing Ads, Apple Search Ads, TikTok, LinkedIn, X, in-house platforms, ...) without touching mureo's source tree. A plugin is a Python package that implements one or more of the Phase 1 Protocols (CampaignProvider, KeywordProvider, AudienceProvider, ExtensionProvider), declares which Capability members it supports, and registers its class under the mureo.providers entry-points group in pyproject.toml. Plugins can also ship their own SKILL.md files via the mureo.skills group.

• docs/plugin-authoring.md — full plugin authoring guide (quick start, Protocols, capabilities, models, skill matching, distribution patterns, security)
• docs/ABI-stability.md — ABI stability promise (what is breaking, what is not, deprecation policy)

Authentication

Interactive Setup (Recommended)

mureo auth setup

The setup wizard walks you through:

1. Google Ads -- Enter Developer Token + Client ID/Secret, open browser for OAuth, select a Google Ads customer account
2. Meta Ads -- Enter App ID/Secret, open browser for OAuth, obtain a Long-Lived Token, select an ad account. Your Meta App can stay in Development Mode -- no App Review is needed since mureo operates your own ad account. You may see a permission warning for business_management during OAuth; this is safe to accept and required for accessing pages managed through Business Portfolio.
3. MCP config -- Automatically writes .mcp.json (project-level) or ~/.claude/settings.json (global) so Claude Code / Cursor can discover the server

Credentials are saved to ~/.mureo/credentials.json. Search Console reuses the same Google OAuth2 credentials as Google Ads -- no additional authentication is required.

credentials.json

{
  "google_ads": {
    "developer_token": "YOUR_DEVELOPER_TOKEN",
    "client_id": "YOUR_CLIENT_ID",
    "client_secret": "YOUR_CLIENT_SECRET",
    "refresh_token": "YOUR_REFRESH_TOKEN",
    "login_customer_id": "1234567890"
  },
  "meta_ads": {
    "access_token": "YOUR_ACCESS_TOKEN",
    "app_id": "YOUR_APP_ID",
    "app_secret": "YOUR_APP_SECRET"
  }
}

Environment variables (fallback)

Verify your setup:

mureo auth status
mureo auth check-google
mureo auth check-meta

MCP Server

Setup with Claude Code

Project-level (recommended) -- add to .mcp.json in your project root:

{
  "mcpServers": {
    "mureo": {
      "command": "python",
      "args": ["-m", "mureo.mcp"]
    }
  }
}

Global -- add to ~/.claude/settings.json:

{
  "mcpServers": {
    "mureo": {
      "command": "python",
      "args": ["-m", "mureo.mcp"]
    }
  }
}

Tip: mureo auth setup can write this configuration automatically.

Setup with Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "mureo": {
      "command": "python",
      "args": ["-m", "mureo.mcp"]
    }
  }
}

Tool list

Google Ads

Meta Ads

Search Console

Rollback

Analysis

CLI

mureo setup claude-code    # One-command setup for Claude Code
mureo setup cursor         # Setup for Cursor
mureo auth status          # Check authentication status
mureo auth check-google    # Verify Google Ads credentials
mureo auth check-meta      # Verify Meta Ads credentials

Strategy Context

Two local files drive strategy-aware operations. Run /onboard to generate them interactively.

• STRATEGY.md -- Persona, USP, Brand Voice, Goals, Operation Mode. See docs/strategy-context.md.
• STATE.json -- Campaign snapshots, action log. Updated automatically by workflow commands.

Architecture

mureo/
├── __init__.py              # Package root
├── auth.py                  # Credential loading (~/.mureo/credentials.json + env vars + Meta token auto-refresh)
├── auth_setup.py            # Interactive setup wizard (OAuth + MCP config)
├── throttle.py              # Rate limiting (token bucket + rolling hourly cap)
├── _image_validation.py     # Image file validation utilities
├── google_ads/              # Google Ads API client (google-ads SDK wrapper)
│   ├── client.py            # GoogleAdsApiClient (8 Mixin: Ads, Keywords, Analysis, Creative, Diagnostics, Extensions, Media, Monitoring)
│   ├── mappers.py           # Response mapping to structured dicts
│   └── _*.py                # 8 Mixin modules (ads, keywords, analysis, extensions, diagnostics,
│                            #   creative, monitoring, media) + validators + classifiers
├── meta_ads/                # Meta Ads API client (15 Mixins, httpx-based)
│   ├── client.py            # MetaAdsApiClient (Campaigns, AdSets, Ads, Creatives, Audiences, Pixels,
│   │                        #   Insights, Analysis, Catalog, Conversions, Leads, PagePosts, Instagram,
│   │                        #   SplitTest, AdRules)
│   ├── mappers.py           # Response mapping to structured dicts
│   └── _*.py                # 15 Mixin modules (campaigns, ads, creatives, audiences, etc.)
├── search_console/          # Google Search Console API client (reuses Google OAuth2 credentials)
│   └── client.py            # SearchConsoleApiClient
├── analytics/               # Per-platform analytics-module Protocol + registry (#120, v0.9.9+)
│   ├── protocol.py          # AnalyticsModule Protocol + AnalyticsCapability
│   ├── registry.py          # Entry-point discovery (`mureo.analytics` group) + fault isolation
│   ├── models.py            # Anomaly / PerformanceDiagnosis / CreativeAudit / BudgetEfficiency
│   └── builtin/             # Built-in adapters for google_ads / meta_ads
├── analysis/                # Cross-platform analysis utilities
│   ├── anomaly_detector.py  # Sample-size-gated anomaly detection (pure function)
│   └── lp_analyzer.py       # Landing page analysis engine
├── context/                 # File-based context (STRATEGY.md, STATE.json)
│   ├── models.py            # Immutable dataclasses (StrategyEntry, StateDocument, ActionLogEntry)
│   ├── strategy.py          # STRATEGY.md parser / renderer
│   ├── state.py             # STATE.json parser / renderer
│   └── errors.py            # Context-related errors
├── rollback/                # Allow-list-gated rollback with append-only audit trail
├── byod/                    # BYOD bundle importer + CSV-backed clients
├── cli/                     # Typer CLI (setup + auth only)
│   ├── main.py              # Entry point (mureo command)
│   ├── setup_cmd.py         # mureo setup claude-code / cursor / codex / gemini
│   └── auth_cmd.py          # mureo auth setup / status / check-*
└── mcp/                     # MCP server
    ├── __main__.py                        # python -m mureo.mcp entry point
    ├── server.py                          # MCP server setup (stdio transport)
    ├── _helpers.py                        # Shared handler utilities
    ├── tools_google_ads.py                # Google Ads tool definitions (aggregator)
    ├── _tools_google_ads_*.py             # Tool definition sub-modules
    ├── _handlers_google_ads.py            # Google Ads base handlers
    ├── _handlers_google_ads_extensions.py # Extensions handlers
    ├── _handlers_google_ads_analysis.py   # Analysis handlers
    ├── tools_meta_ads.py                  # Meta Ads tool definitions (aggregator)
    ├── _tools_meta_ads_*.py               # Tool definition sub-modules
    ├── _handlers_meta_ads.py              # Meta Ads base handlers
    ├── _handlers_meta_ads_extended.py     # Extended handlers
    ├── _handlers_meta_ads_other.py        # Other handlers
    ├── tools_search_console.py            # Search Console tool definitions
    └── _handlers_search_console.py        # Search Console handlers

Design principles:

• No database -- all state is either in the ad platform APIs or in local files (STRATEGY.md, STATE.json).
• No LLM dependency -- mureo does not embed an LLM. Inference, planning, and decision-making are the agent's responsibility.
• Immutable data models -- all dataclasses use frozen=True to prevent accidental mutation.
• Credentials stay local -- loaded from ~/.mureo/credentials.json or environment variables. Never sent anywhere except the official ad platform APIs.

Development

git clone https://github.com/logly/mureo.git && cd mureo
pip install -e ".[dev]"
pytest tests/ -v                              # run tests
pytest --cov=mureo --cov-report=term-missing  # with coverage
ruff check mureo/ && black mureo/ && mypy mureo/  # lint & format

Python 3.10+ required. See CONTRIBUTING.md for full development guidelines.

License

Apache License 2.0