Set up Amazon Q Developer
AWS’s AI coding assistant. Add Agentcy so Amazon Q can access your marketing data in the CLI or IDE while building and deploying applications. Free tier supports MCP.
- 01
Sign up at app.goagentcy.com and create an API key
- 02
VS Code / JetBrains UI: install the Amazon Q Developer extension and open the Amazon Q Chat panel
- 03
Click the Tools (wrench) icon, then the + symbol
- 04
Choose Global (all projects) or Local (current workspace)
- 05
Name: agentcy | Transport: http | URL: https://data.goagentcy.com/mcp
- 06
Add Header — Key: Authorization, Value: Bearer YOUR_AGENTCY_API_KEY
- 07
Click Save and approve tool permissions when prompted
path: ~/.aws/amazonq/default.json
{
"mcpServers": {
"agentcy": {
"type": "http",
"url": "https://data.goagentcy.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_AGENTCY_API_KEY"
}
}
}
}Amazon Q Free tier ($0/month, 50 agentic requests/month) fully supports MCP. The "type": "http" field is REQUIRED for remote HTTP servers. Preferred config path is ~/.aws/amazonq/default.json (workspace: .amazonq/default.json). The legacy ~/.aws/amazonq/mcp.json still works but is being phased out. Pro tier ($19/user/month) adds org-wide MCP server whitelisting for admins. Alternative: edit the JSON file directly with the snippet below. Workspace config overrides global config when both exist.
Stuck or want to verify these instructions yourself? These are the documentation sources we used. If something here doesn't match what you see in your client, the vendor may have updated their UI — and we'll get this page updated.
After connecting Amazon Q Developer and configuring your data sources in the portal, ask questions about any of them in natural language: