
Maasy — AI Marketing Copilot
io.github.JbelievePublished by GitHub account Jbelievev1.3.1Updated Nov 3, 2026
AI marketing copilot: brand intelligence, campaigns, content, CRM, SEO, and skills for Claude.
Overview
Maasy MCP server connects Claude to a Maasy marketing account for brand intelligence, campaigns, CRM, SEO and content generation.
- What you can do
- Read brand data: list brands with health status, run a deep brand scan, fetch brand DNA, pending alerts and daily summaries
- Read performance metrics: campaign spend, CTR, CPC and ROAS, CRM pipeline and lead summary, content pipeline, SEO/GEO status
- Generate marketing content and discover SEO keywords
- Execute marketing actions such as reports, budget redistribution, creative rotation and lead-score recalculation
- Manage Maasy skills: list, read, create, update and delete copilot knowledge skills
- When to use it
- Useful when you already run marketing in Maasy and want to ask Claude about brand health, campaign performance, CRM pipeline or SEO, or have it draft content and trigger marketing actions from Claude Desktop or Claude Code.
- Requirements
- Runs locally over stdio via npx, so Node.js 18+ is needed, plus a Maasy account and an API key set in MAASY_API_KEY. MAASY_SUPABASE_URL points at the Maasy API endpoint and MAASY_PROJECT_ID optionally sets a default brand. A Claude Desktop or other MCP-compatible client is required.
Installation
In SourceWeft
- Open Maasy — AI Marketing Copilot in the dashboard and add it to a workspace.
- 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
@maasy-ai/mcp-server
MCP server for Maasy — connect Claude to your marketing intelligence.
Give Claude direct access to your brand DNA, campaigns, CRM, SEO, and content pipeline. Ask Claude to scan your brand, generate content, redistribute ad budget, or create marketing skills — all from Claude Desktop or Claude Code.
Quick install
Claude Desktop (one click)
Go to Maasy → Settings → API / MCP and click "Instalar en Claude Desktop". Done.
Manual setup
Step 1: Get your API key from Maasy Settings → API / MCP
Step 2: Add to your Claude Desktop config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Step 3: Restart Claude Desktop. Maasy appears in your MCP connectors.
What you can do
Brand intelligence
- Scan brand health: DNA completeness, campaigns, content, CRM, SEO, alerts
- Get full brand DNA: tone of voice, ICP, value proposition, assets, references
- List all brands with traffic-light status
Marketing actions
- Generate on-brand social content for any platform
- Discover SEO keywords
- Rotate fatigued ad creatives
- Redistribute budget between campaigns
- Diagnose underperforming campaigns
- Recalculate CRM lead scores
- Fill content calendar gaps
Skills — teach Maasy new knowledge
- Create specialized skills (e.g. "TikTok expert for pet brands")
- List, edit, and delete existing skills
- Maasy uses skills in the copilot automatically
Daily intelligence
- Campaign metrics: spend, CTR, CPC, ROAS
- CRM summary: hot leads, contacts, opportunities, pipeline value
- Content pipeline by status and network
- SEO/GEO visibility, mentions, citations
- Pending alerts that need attention
- Daily consolidated operations summary
Example prompts
Tools reference
Requirements
- Node.js 18+
- A Maasy account
- Claude Desktop or any MCP-compatible client
Built by the Maasy team
Source: README.md at commit c07501e
Tools
0Version history
1- v1.3.1LatestSep 16, 2026
Score
40% 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
Declare a license in the repository or the registry entry.