Connect your Coding Agent

The modeling MCP tools are for building models. To let your coding agent analyze data with your published models — the same governed access as workspace chat — connect it to the consumption MCP server and authenticate with OAuth. Use your organization’s MCP server URL: https://<your-org>.mcp.credibledata.com/mcp (see MCP Tools for workspace scoping).

Using Cursor? The VS Code Extension covers it. Connecting a personal chat client like Claude, ChatGPT, or Gemini instead? See Connect your Agent.

VS Code Copilot
Claude Code
Gemini CLI
Windsurf

Open the Command Palette (Cmd+Shift+P on Mac, Ctrl+Shift+P on Windows/Linux) and run “MCP: Add Server”
Select HTTP
Enter your organization’s MCP URL: https://<your-org>.mcp.credibledata.com/mcp
Enter a server ID for the server (e.g., “credible”)
Press Enter and select “Global” or “Workspace” scoped
A popup should redirect you to the OAuth flow — open it in your browser and complete the authentication
The server should now show as “Running” (with a checkbox) in the mcp.json file
Open Copilot to test it out

Requires a Pro or Max subscription plan

# Add MCP server
claude mcp add --transport http CredibleData https://<your-org>.mcp.credibledata.com/mcp

# Start Claude Code
claude

# Inside Claude Code prompt, authenticate
/mcp
# Select "authenticate"

# Install Gemini CLI
npm install -g @google/gemini-cli

# Add MCP server
gemini mcp add -t http CredibleData https://<your-org>.mcp.credibledata.com/mcp

# Run gemini to complete OAuth flow
gemini
# This will open a browser window for authentication

# Verify the server is connected
gemini mcp list

In the agent window, click on the plug icon
Click Settings — this opens the mcp_config.json file
Add your server configuration:

{
  "mcpServers": {
    "CredibleData": {
      "serverUrl": "https://<your-org>.mcp.credibledata.com/mcp"
    }
  }
}

Save the file — this automatically opens the OAuth authentication flow
Complete the authentication in your browser

Once connected, your agent has the get_context and execute_query tools — the same tools that power workspace chat.

Next Steps

MCP Tools

The tool reference — what get_context and execute_query do and how to call them

Discovery

Better answers start in the model — enrich it with doc and index annotations

Get Started

Semantic Data Modeling

Context Engine

Developers

Admins

Concepts

Support

Reference

Connect your Coding Agent

Next Steps

MCP Tools

Discovery

​Next Steps

MCP Tools

Discovery

Next Steps