Skip to main content
This guide walks you through building a chat-style workflow that lets an n8n AI Agent call Explorium’s Model Context Protocol (MCP) tools, powered by Anthropic’s Claude. You’ll end up with a flow like this:

​
1. Prerequisites

RequirementNotes
n8n @ v1.31+Self-hosted or Cloud
Explorium API keyGet one from your AgentSource Admin Panel
Anthropic API keyNeeded for Claude 3.x Sonnet
SSE endpointhttps://mcp.explorium.ai/mcp

​
2. Create Your Flow

1

Trigger

When chat message received (built-in)
2

AI Agent

type: Tools Agent
3

Anthropic Chat Model

Claude 3.7 Sonnet
4

Memory

simple in-flow memory
5

MCP Client

calls Explorium tools
Connect the nodes just like the overview image (dotted lines = resource connections).

​
3. Configure Each Node

​
3.1 AI Agent configuration

SettingValue
AgentTools Agent
Source for PromptConnected Chat Trigger Node
System MessageUse a Claude-style system prompt. Example: The assistant is Claude, created by Anthropic. The current date is {{ Date() }}.\nYou are powered by Explorium’s MCP tools. Always call tools when data is required…
Chat ModelConnect the Anthropic Chat Model node
ToolConnect the MCP Client node
MemoryConnect the Memory node

​
3.2 Anthropic Chat Model

  • Credential: the Anthropic account you just created
  • Model: Claude 3.7 Sonnet
  • Enable Thinking: On (optional, shows the “thinking” indicator)

​
3.3 Anthropic credential

Enter your Anthropic key and test – you should see Connection tested successfully.

​
3.4 MCP Client node

FieldValue
SSE Endpointhttps://mcp.explorium.ai/mcp
AuthenticationHeader Auth
Credential for Bearer AuthHeader Auth account
Tools to includeAll
Fill the header fields:
  • Name: api_key
  • Value: <Enter your api key>

​
4. Test It Out

1
Click Open chat at the bottom of the canvas.
2
Ask something data-centric, e.g.
  • “Who is the CMO of Snowflake?”
3
You should see the MCP Client fire Match Businesses ➜ Enrich Businesses and Claude respond with a neatly-formatted answer.

​
Happy prospecting!