Overview
You can easily create an agent using the Rippletide Trust Platform and expose it as an MCP server, ready to be plugged into any MCP-compatible agent or client.Step 1: Build your Agent
Go to the Rippletide Builder and define your agent’s:- Knowledge: the data and context your agent can access
- Processes: the workflows and actions it can perform
- Guardrails: the safety rules and constraints it must follow
Step 2: Visualize and Test
Navigate to the Knowledge tab to visualize your agent’s context graph and test it interactively before going live.Step 3: Add to your Agent
Go to the Launch page. You will see MCP Tools and the exposed tools for your agent. Copy the configuration for your favorite MCP-compatible client:Claude Desktop
Claude Desktop
Add the following to your
claude_desktop_config.json file:- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Claude Code (CLI)
Claude Code (CLI)
Run the following command in your terminal:Or add it to your
.claude/settings.json:Cursor
Cursor
Add the following to your
.cursor/mcp.json file at the root of your project (or globally in ~/.cursor/mcp.json):Windsurf
Windsurf
Add the following to your
~/.codeium/windsurf/mcp_config.json:VS Code (GitHub Copilot)
VS Code (GitHub Copilot)
Add the following to your Or add it to your VS Code
.vscode/mcp.json file at the root of your project:settings.json under mcp:Custom Agent / SDK
Custom Agent / SDK
Use any MCP-compatible SDK or framework. Point your MCP client to the following URL:The server supports Streamable HTTP transport.