Clazar MCP Server
Last updated: April 11, 2026
The Clazar MCP Server connects your Clazar account to AI assistants like Claude, ChatGPT, Cursor, and Windsurf via the Model Context Protocol (MCP) — an open standard that lets AI assistants securely connect to external data sources. Ask your AI assistant about your cloud marketplace data — offers, contracts, co-sell, revenue, and more — across AWS, Azure, and GCP, using natural language.
What You Can Do
Once connected, you can ask your AI assistant questions about your cloud marketplace data across AWS, Azure, and GCP — including offers, contracts, co-sell pipelines, revenue analytics, and more.
"Show me all pending offers across AWS, Azure & GCP"
"Which contracts are expiring in the next 90 days?"
"What does my co-sell pipeline look like?"
"Show me recent metering records for my Azure products"
"What are my AWS disbursements this month?"
All capabilities work across AWS, Azure, and GCP in the same session — no need to ask separately for each cloud.
Prerequisites
An active Clazar account with MCP access enabled. If MCP isn't yet enabled for your account, please contact Clazar support and we'll get it turned on for you.
Any AI platform that supports the Model Context Protocol (MCP) — setup instructions for popular platforms are provided below
You must be an Owner or Admin of the AI assistant/platform where you're adding the MCP server — standard user permissions may not allow adding custom connectors
Setup Instructions
No API keys or client secrets needed. Simply add the Clazar MCP server URL as a custom connector in your AI platform and authenticate via your browser.
MCP Server URL:
https://mcp.clazar.ioClaude Desktop
Open Claude Desktop → Settings → MCP Servers
Click Add Custom MCP Server
Enter the server URL:
https://mcp.clazar.ioClick Connect — a browser window will open
Sign in with your Clazar credentials and approve the connection
You're all set! Start asking Claude about your Clazar data
Claude Code (CLI)
Open your terminal and run:
claude mcp add --transport http clazar-mcp https://mcp.clazar.ioOpen Claude Code and run the
/mcpcommandSelect clazar-mcp — authenticate in the browser when prompted
Start querying your data
ChatGPT (with MCP support)
Open ChatGPT → Settings → Connected Tools (or MCP Connectors)
Click Add Connector
Enter the server URL:
https://mcp.clazar.ioAuthenticate via the browser popup with your Clazar credentials
Once connected, ChatGPT can call Clazar tools in your conversations
Cursor
Open Cursor → Settings → MCP
Click Add new MCP server
Set the type to HTTP and enter the URL:
https://mcp.clazar.ioSave and authenticate when the browser opens
Cursor's AI can now access your Clazar data while you work
Windsurf
Open Windsurf → Settings → MCP Servers
Add a new server with URL:
https://mcp.clazar.ioAuthenticate via the browser when prompted
You're connected — start asking questions in the AI panel
Other MCP-Compatible Platforms
Any platform that supports the Model Context Protocol (MCP) with HTTP transport can connect to Clazar. The general steps are:
Find the MCP or Custom Connector settings in your platform
Add a new server with URL:
https://mcp.clazar.ioAuthenticate via browser when prompted
Start using Clazar tools
Security
The Clazar MCP Server uses OAuth 2.1 with PKCE for authentication — no API keys or client secrets to manage. You sign in with your existing Clazar credentials, and every request is scoped to your authenticated account. The same permissions and access controls that apply in the Clazar platform apply through the MCP server — you can only access the data you're authorized to see. Clazar does not persist any data from MCP sessions.
Troubleshooting
Authentication fails: Make sure your Clazar account has MCP access enabled. Contact Clazar support to get MCP enabled for your account.
Server not responding: Verify the URL is exactly
https://mcp.clazar.iowith no trailing slash or extra characters.Tools not appearing: After authenticating, restart your AI assistant or refresh the MCP connection.
Need help? Reach out to your Clazar point of contact or email us at support — we're happy to help you get set up.