mcpField
A
Agentcy - Your AI Marketing Agent

Agentcy - Your AI Marketing Agent

Remote
github.com/goagentcyAI & Agents4Updated 28w ago
Repository

About Agentcy - Your AI Marketing Agent

Agentcy is a managed AI marketing analyst for marketing teams and client-service professionals. It connects marketing data sources and returns synthesized insights and recommendations through a compact MCP interface.

Key features

  1. 01Analyze data across marketing sources
  2. 02Synthesize findings into recommendations
  3. 03Switch client data with a domain parameter
  4. 04Connect through four MCP tools
  5. 05Support for analytics, ads, SEO, and commerce

Use cases

  1. 01Compare organic traffic across periods
  2. 02Find campaigns wasting advertising budget
  3. 03Review competitor keywords and technologies
  4. 04Analyze site speed and prioritize fixes

MCP support

Provides a hosted Streamable HTTP MCP server at https://data.goagentcy.com/mcp. MCP clients authenticate with a Bearer token API key and access marketing analysis through four tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://data.goagentcy.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://data.goagentcy.com/mcpAuth required

Tools

Details

From the project README

Agentcy

Agentcy

The AI marketing analyst that lives inside your favorite AI tools.
Ask about your clients' marketing. Get insights and recommendations back — not raw data.

Website • Docs • Pricing • Integrations


What is Agentcy?

Agentcy is an AI marketing analyst that works inside the AI tools you already use. Ask questions about your clients' marketing in plain English — Agentcy analyzes the data across GA4, Search Console, Google Ads, WooCommerce, and more, then delivers synthesized insights and recommendations. Not a data dump. Not a spreadsheet. An analyst.

What makes it different:

  • Analyst, not a data pipe — every response is a synthesized insight with recommendations, not raw JSON
  • One connection, all your data — GA4, GSC, Google Ads, WooCommerce, YouTube, GTM, HubSpot, SpyFu, and more
  • Switch clients instantly — use the domain parameter to query any client's data
  • Minimal overhead — 4 MCP tools, ~630 tokens vs. 100+ tools from separate MCPs
  • Works everywhere — Claude, ChatGPT, Cursor, VS Code, Windsurf, OpenClaw, and more

Quick Start

1. Get your API key

Sign up at goagentcy.com and create an API key in the portal.

2. Connect your AI assistant

Pick your client below and add the configuration.

Client Configurations

Claude Desktop

Use the Connectors UI: Settings → Connectors → Add → enter server URL and API key.

Or add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentcy": {
      "url": "https://data.goagentcy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
Claude Code
claude mcp add agentcy \
  --transport http \
  https://data.goagentcy.com/mcp \
  --header "Authorization: Bearer YOUR_AGENTCY_API_KEY"
ChatGPT

Use the ChatGPT UI: Settings → Connectors → Add MCP Server → enter server URL and API key.

Cursor

Add to .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:

{
  "mcpServers": {
    "agentcy": {
      "url": "https://data.goagentcy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
VS Code (GitHub Copilot)

Add to .vscode/mcp.json in your project or user settings:

{
  "servers": {
    "agentcy": {
      "type": "http",
      "url": "https://data.goagentcy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "agentcy": {
      "serverUrl": "https://data.goagentcy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
Cline
{
  "mcpServers": {
    "agentcy": {
      "url": "https://data.goagentcy.com/mcp",
      "type": "streamableHttp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
Roo Code
{
  "mcpServers": {
    "agentcy": {
      "type": "streamable-http",
      "url": "https://data.goagentcy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
JetBrains IDEs

Add to your MCP configuration (Settings → Tools → AI Assistant → MCP Servers):

{
  "mcpServers": {
    "agentcy": {
      "url": "https://data.goagentcy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
Gemini CLI / Gemini Code Assist

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "agentcy": {
      "httpUrl": "https://data.goagentcy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AGENTCY_API_KEY"
      }
    }
  }
}
Codex CLI

Add to ~/.codex/config.toml:

[mcp_servers.agentcy]
url = "https://data.goagentcy.com/mcp"
bearer_token_env_var = "AGENTCY_API_KEY"
Mistral Le Chat

Use the Le Chat UI: Settings → Connectors → Add custom connector → enter server URL and API key.

Other MCP Clients

Agentcy works with any MCP client that supports Streamable HTTP transport. Use this configuration:

  • Server URL: https://data.goagentcy.com/mcp
  • Transport: Streamable HTTP
  • Authentication: Bearer token (your agcy_ API key)

See the full list of supported clients at goagentcy.com/integrations.

Data Sources

SourceCategoryAuth
Google Analytics 4AnalyticsGoogle OAuth
Google Search ConsoleSearch / SEOGoogle OAuth
Google AdsAdvertisingGoogle OAuth
YouTube AnalyticsVideo / ContentGoogle OAuth
Google Tag ManagerTag ManagementGoogle OAuth
Google SheetsData / SpreadsheetsGoogle OAuth
WooCommerceE-commerceAPI Key (BYOK)
HubSpotCRM / MarketingAPI Key (BYOK)
SpyFuCompetitive IntelAPI Key (BYOK)
Web IntelligenceResearchIncluded
PageSpeed InsightsPerformanceIncluded
DNS LookupInfrastructureIncluded
SSL/TLS AnalysisSecurityIncluded
WHOIS / RDAPDomain InfoIncluded
Sitemap AnalysisSEO / TechnicalIncluded
Schema MarkupSEO / Structured DataIncluded
Readability AnalysisContentIncluded
Technology DetectionCompetitive IntelIncluded
Data VisualizationReportingIncluded

Example Questions

"How did organic traffic perform last month vs the previous month?"
"What are my top 10 landing pages by conversion rate?"
"Show me my Google Ads campaigns — which ones are wasting budget?"
"What keywords is my competitor ranking for that I'm not?"
"Analyze my site speed and give me the top 3 fixes."
"What technologies is competitor.com using?"
"How are my YouTube videos performing this quarter?"
"Pull my latest WooCommerce orders and revenue trends."

Links

License

Configuration files and documentation in this repository are licensed under the MIT License. The Agentcy MCP server is a hosted service — see goagentcy.com/terms for service terms.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.