# Botsonic MCP MCP

> Botsonic connects your custom AI chatbot system to any agent, letting you train bots on private documents and websites. Manage an entire fleet of support chatbots from one place, check performance analytics, and capture leads without switching dashboards.

## Overview
- **Category:** customer-support
- **Price:** Free
- **Tags:** chatbot-training, rag, knowledge-base, ai-support, customer-service, no-code-ai

## Description

You can manage a full suite of specialized AI assistants using this MCP. Train your bot on all your company's web pages and internal documents by adding URLs to its knowledge base. From there, you get real-time chat responses, letting customers ask questions and getting instant, accurate answers based only on your provided data. You don't have to manually track conversations; the system logs every interaction, so you can browse full conversation histories for any bot. It also automatically captures leads during chats and gives you performance analytics—tracking how many messages were sent or what the resolution rate is. Connecting this MCP through Vinkius means your agent has access to a massive catalog of tools, keeping all your support processes managed from one place.

## Tools

### add_knowledge_url
Adds a specified website URL to a bot's knowledge base for training.

### check_botsonic_status
Verifies that the connection and API credentials are active and working.

### create_bot
Sets up a new, blank chatbot instance with customizable instructions and personality.

### get_bot
Retrieves the full details of a single, specific bot by its ID.

### get_bot_analytics
Fetches usage metrics and performance statistics for an existing chatbot.

### get_conversation
Retrieves the complete message transcript for a single, specific chat session.

### list_bots
Returns a list of every chatbot configured under your account.

### list_conversations
Lists available conversation IDs, allowing you to select which chat history to view.

### list_knowledge_base
Shows a list of all current sources (URLs and files) used for bot training.

### list_leads
Pulls a compiled record of all contact information gathered as leads during customer chats.

### send_message
Sends a direct message to a bot, triggering an AI response in real time for testing or querying.

### update_bot
Modifies the settings, instructions, or knowledge base of an existing chatbot instance.

## Prompt Examples

**Prompt:** 
```
List all my bots and show the analytics for the one with the most conversations.
```

**Response:** 
```
You have 4 bots configured. 'Customer Support Bot' (bot_301) leads with 1,284 conversations this month. Running analytics... Resolution rate: 78%, average satisfaction: 4.2/5, total messages: 8,921. The second most active is 'Sales Assistant' (bot_302) with 456 conversations. Would you like to inspect specific conversations or review the knowledge base?
```

**Prompt:** 
```
Add our pricing page and help center to the 'Sales Assistant' bot's knowledge base.
```

**Response:** 
```
Adding 2 URLs to bot 'Sales Assistant' (bot_302)... ✅ https://example.com/pricing — crawled successfully, 3 pages indexed. ✅ https://help.example.com — crawled successfully, 28 articles indexed. The bot's knowledge base now has 14 sources total (8 URLs, 4 documents, 2 text snippets). The new content will be available in responses within 2-3 minutes.
```

**Prompt:** 
```
Show me all leads captured by the 'Customer Support Bot' this week.
```

**Response:** 
```
Found 18 leads captured by bot_301 this week. Top 5 by engagement: 1) Sarah Chen (sarah@techcorp.io) — asked about enterprise pricing, 4 messages. 2) James Miller (james@startupxyz.com) — demo request, 3 messages. 3) Lisa Park (lisa@retailco.com) — integration question, 6 messages. Average lead quality score: 7.2/10. Would you like to export these leads or view specific conversation transcripts?
```

## Capabilities

### Manage Bot Profiles
Create and update individual chatbot configurations, setting specific personalities and instructions for each bot.

### Feed Knowledge to Bots
Add external websites and documents to a bot's knowledge base so it can answer questions using your proprietary data.

### Analyze Bot Performance
Retrieve analytics on usage metrics, including total conversation volume or average customer satisfaction scores.

### View Conversation Details
Access and review the full message history for any specific chat session across all your bots.

### Capture Sales Leads
Retrieve a list of contacts that were automatically captured as leads during customer conversations.

## Use Cases

### The Support Team Needs Full Visibility
A support manager needs to know why a customer was unhappy last week. Instead of checking three different systems, they use `list_conversations` and then call `get_conversation`. They get the full transcript in one place, allowing them to immediately identify process gaps.

### The Product Team Needs to Test a New Feature
A product manager just updated the pricing structure. They use `add_knowledge_url` to feed the new documentation into the bot and then run several tests using `send_message`. This confirms the bot answers correctly before going live.

### The Sales Team Needs a Lead Report
A sales representative wants to review all potential clients from the last month. They simply call the function that lists captured leads, which returns names, emails, and key topics discussed, ready for immediate follow-up.

### The Operations Team Needs a Status Check
Before a major launch, an engineer needs to ensure all services are running. They check the bot's details using `get_bot` and run the connection status tool to confirm everything is ready for high traffic.

## Benefits

- You stop manually gathering usage stats. By calling `get_bot_analytics`, you get immediate metrics like resolution rate and message count, letting you pinpoint which bots need tuning right away.
- Forget switching tabs to track who's interested in buying. The tool that lists captured leads automatically aggregates contact data from chat sessions, giving your growth team a clean list of prospects.
- You can build new assistants instantly using `create_bot`. You just set the personality and goals; the MCP handles the underlying infrastructure for you.
- Need to test how the bot responds to a specific question? Use `send_message` to simulate a live chat session right from your agent, getting instant feedback on its performance.
- When company documentation changes, you don't have to manually update everything. Just use the function that adds knowledge URLs to feed new web content into the bots instantly.

## How It Works

The bottom line is that your agent treats the entire collection of bots like one single service endpoint, letting you manage everything without needing multiple API keys or dashboards.

1. Subscribe to this MCP and input your unique Botsonic API token from the Writesonic dashboard.
2. Your AI client authenticates and gains access to all bot management tools, allowing you to list or create new chatbot instances.
3. You can then send messages directly to a bot or check its performance metrics by calling specific functions.

## Frequently Asked Questions

**How do I train the chatbot using the add_knowledge_url tool?**
You call the function with one or more URLs. The bot crawls those sites and indexes the content, making it available to answer questions based on that specific web data.

**What is the difference between list_bots and get_bot?**
`list_bots` gives you a summary of all bots you have set up. `get_bot` requires a specific bot ID, giving you the full configuration details for just that one bot.

**Can I check if my bot is working without sending a message?**
Yes, use the check_botsonic_status tool. It verifies your API connection and overall account status to ensure you can manage all functions successfully.

**How do I get lead data using list_leads?**
Simply call list_leads. This function aggregates contact information captured during chats, providing a clean record of potential customers for follow-up.

**When I use the `create_bot` tool, what essential parameters do I need to define?**
You must provide a bot name, core instructions, and initial personality traits. These settings determine how your agent behaves from day one. You can also link it to a knowledge base immediately upon creation.

**How does the `get_bot_analytics` tool help me monitor my AI chatbot's performance?**
This tool pulls key metrics like conversation volume, resolution rate, and customer satisfaction scores. It lets you pinpoint which bots need immediate attention or training adjustments.

**Can I use the `list_conversations` tool to find chat history for a specific time frame?**
Yes, the tool lists all conversations and allows filtering by date range and bot ID. You can quickly narrow down the records instead of manually sifting through every session.

**If I need to change my existing bot's behavior, what does the `update_bot` tool allow me to modify?**
You can use this tool to revise the bot’s core instructions, adjust its personality profile, or swap out knowledge base sources without rebuilding the entire agent.