Skip to content
Choose an available topic from the sidebar. More documentation is coming soon.

Advanced

Expose Your Knowledge Base via MCP

Let AI agents like Claude, Cursor, and Windsurf query your chatbot’s knowledge base directly using the Model Context Protocol. Includes automatic WebMCP browser discovery.

Every SiteSpeakAI chatbot can act as an MCP (Model Context Protocol) server, giving AI agents direct access to your knowledge base. Instead of scraping your website or chat widget, agents connect to a structured endpoint and get accurate, sourced answers from your trained content.

SiteSpeakAI supports two ways for AI agents to access your knowledge base:

  1. MCP Server endpoint – AI tools like Claude Desktop, Cursor, and Windsurf connect directly to your chatbot’s MCP endpoint. Requires manual configuration in each tool.
  2. WebMCP (browser discovery) – AI agents running in the browser automatically discover your knowledge base through the chatbot widget. No configuration needed.

MCP Server and WebMCP are available on Pro, Pro Plus, and Business plans. Each plan includes a monthly query allowance (Pro: 1,000 / Pro Plus: 2,500 / Business: 10,000).

Why expose your knowledge base via MCP?

AI agents are becoming the primary way people find and interact with information. When a developer asks Cursor about your API, or a user asks Claude about your product, those agents need a reliable source of truth. Your MCP server provides that.

How it works

When an AI agent connects to your MCP server endpoint, it gets access to one tool:

query_knowledge_base - Searches your chatbot’s trained content using the full RAG pipeline (vector search, query expansion, and Cohere reranking). Returns relevant content chunks with source URLs.

The agent sends a natural language query, and your MCP server returns the most relevant content from your training sources - the same content your chatbot uses to answer questions.

Enable MCP Server

1

Go to Settings

In your chatbot dashboard, select your chatbot and go to Settings.

2

Open Advanced settings

Click the Advanced tab.

3

Find MCP Server

Scroll down to the MCP Server (Public Access) section.

4

Enable public access (optional)

Toggle Public MCP Access to allow AI agents to query your knowledge base without authentication.
When disabled, agents need a valid API token to connect (see Authentication below).

5

Copy your endpoint URL

Click the copy button next to your MCP Endpoint URL. This is the URL AI agents will use to connect.
Your endpoint URL follows this format:

				
					
				
			

6

Save settings

Click Save to apply your changes.

Get Your API Credentials

SiteSpeakAI integrates with WhatsApp Business to let your AI chatbot respond to customer messages on WhatsApp. This guide walks you through setting up the WhatsApp Business API and connecting it to your SiteSpeakAI chatbot.

1

Get your Phone Number ID

In WhatsApp > API Setup, find your verified phone number. The Phone Number ID is displayed below the number (a long numeric string like 123456789012345).

2

Generate a Permanent Access Token

By default, Meta provides a temporary access token that expires in 24 hours. For production use, you need a permanent token:

  1. Go to Business Settings at business.facebook.com/ settings
  2. Navigate to Users > System Users
  3. Click Add to create a new system user (if you don’t have one)
  4. Give it a name like “WhatsApp API” and select Admin role
  5. Click Add Assets, select your WhatsApp app, and enable Full control
  6. Click Generate new token, select your app, and check whatsapp_business_messaging and whatsapp_business_management
  7. Copy the generated token – this is your permanent access token

3

Get your App Secret

Go back to your app in the Meta Developer Dashboard. Navigate to App settings > Basic. Click Show next to the App Secret field and copy it.

Connect to SiteSpeakAI

1

Go to Deploy & Install

In your SiteSpeakAI dashboard, select your chatbot and go to Deploy & Install.

2

Select WhatsApp

Click on the WhatsApp tab.

3

Enter your credentials

Fill in the three fields:

  • Phone Number ID – The numeric ID from Meta’s API Setup page
  • Access Token – Your permanent access token from the system user
  • App Secret – Your app secret from App Settings > Basic

4

Click Connect

Click the Connect button. SiteSpeakAI will generate a Webhook URL and Verify Token for you.

Configure the Webhook in Meta

After connecting in SiteSpeakAI, you need to configure the webhook in your Meta Developer App:

1

Go to WhatsApp Configuration

In your Meta Developer App, navigate to WhatsApp > Configuration.

2

Enter the webhook details
  • Callback URL: Paste the Webhook URL from SiteSpeakAI
  • Verify token: Paste the Verify Token from SiteSpeakAI

Click Verify and save.

3

Subscribe to messages

Navigate back to WhatsApp > Configuration. Under Webhook fields, find the messages field and click Subscribe.

Test Your Integration

After connecting in SiteSpeakAI, you need to configure the webhook in your Meta Developer App:

During development, you can only send messages to phone numbers that have been added as test numbers in your Meta app. To message any WhatsApp user, you’ll need to complete Meta’s business verification process.

Troubleshooting

Messages not being received

Messages not being sent

Webhook verification failing

Going Live

To send messages to any WhatsApp user (not just test numbers), you’ll need to:

  1. Complete Business Verification – Verify your business in Meta Business Settings
  2. Request Production Access – In your app’s WhatsApp settings, request to go live
  3. Add a Payment Method – WhatsApp Business API charges per conversation (first 1,000 conversations per month are free)

For detailed information, see Meta’s WhatsApp Business documentation.

Ready to automate your customer service with AI?

Join over 1000+ businesses, websites and startups automating their customer service and other tasks with a custom trained AI agent.