Botsonic MCP. Train your chatbots on proprietary data sources.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
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.
What your AI agents can do
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.
Create and update individual chatbot configurations, setting specific personalities and instructions for each bot.
Add external websites and documents to a bot's knowledge base so it can answer questions using your proprietary data.
Retrieve analytics on usage metrics, including total conversation volume or average customer satisfaction scores.
Access and review the full message history for any specific chat session across all your bots.
Retrieve a list of contacts that were automatically captured as leads during customer conversations.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Botsonic: 12 Tools for Bot Management
Use these twelve tools to create, configure, analyze, and manage every aspect of your chatbot fleet, from knowledge ingestion to lead tracking.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Botsonic on Vinkius019dd0c4add knowledge url
Adds a specified website URL to a bot's knowledge base for training.
019dd0c4check botsonic status
Verifies that the connection and API credentials are active and working.
019dd0c4create bot
Sets up a new, blank chatbot instance with customizable instructions and personality.
019dd0c4get bot
Retrieves the full details of a single, specific bot by its ID.
019dd0c4get bot analytics
Fetches usage metrics and performance statistics for an existing chatbot.
019dd0c4get conversation
Retrieves the complete message transcript for a single, specific chat session.
019dd0c4list bots
Returns a list of every chatbot configured under your account.
019dd0c4list conversations
Lists available conversation IDs, allowing you to select which chat history to view.
019dd0c4list knowledge base
Shows a list of all current sources (URLs and files) used for bot training.
019dd0c4list leads
Pulls a compiled record of all contact information gathered as leads during customer chats.
019dd0c4send message
Sends a direct message to a bot, triggering an AI response in real time for testing or querying.
019dd0c4update bot
Modifies the settings, instructions, or knowledge base of an existing chatbot instance.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Botsonic, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Botsonic. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
The Headache of Scattered Support Data
Today, when a customer asks an advanced question, your team has to manually check the ticketing system for history, open a separate wiki page to find the correct procedure, and then copy-paste relevant details into a summary report. This process is slow, requires multiple people' logins, and usually results in missing context or incomplete records.
With this MCP, your agent handles it all automatically. The bot pulls information from your entire knowledge base using only one interaction. You get accurate answers instantly, freeing up agents to handle complex cases that actually require human judgment.
View Bot Performance and Leads with Botsonic
Previously, gathering key business insights meant running reports in the ticketing system, exporting them to a spreadsheet, and then manually cross-referencing those leads against your CRM. This was tedious work for Growth teams.
Now you can simply ask your agent to get bot analytics or list captured leads. You get clean data structures that immediately show engagement metrics and qualified contacts without ever opening a second dashboard.
What you can do with this MCP connector
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.
019dd0c5-0374-7287-93b5-958c697c6413 
How Botsonic MCP Works
- 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.
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.
Who Is Botsonic MCP For?
Product Managers and Growth Leads who struggle with manually feeding new documentation to support agents. It’s also for Customer Support Ops Engineers tired of jumping between the ticketing system, knowledge base tool, and analytics dashboard just to understand one chat thread.
Monitoring live bot conversations, reviewing resolution rates, and finding captured leads without leaving their primary operational dashboard.
Testing new bot responses or training bots with updated internal documentation before rolling them out to the public.
Analyzing engagement metrics across different chatbot functions and tracking lead quality performance over time.
What Changes When You Connect
- 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_messageto 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.
Real-World 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.
The Tradeoffs
Treating bots like single-purpose FAQs
Only configuring a bot with general knowledge base URLs. This results in generic answers that don't account for the user's specific role or context, leading to frustrated customers.
→
Use get_bot and update_bot to define a specific personality, instructions, and purpose for each bot. For example, create a 'Billing Bot' and a separate 'Technical Support Bot' to keep answers focused.
Ignoring conversation context
Asking the agent to only look at the current chat transcript without reviewing past interactions or lead data. The bot fails because it lacks historical context.
→
Always check list_conversations first, then use get_conversation. If you suspect a sales opportunity, follow up by calling the function that lists captured leads.
Manual data transfer
A human copying conversation summaries from one dashboard and pasting them into a spreadsheet. This is slow, error-prone, and never captures real-time metrics.
→ Use the performance analytics tool to get aggregated data like resolution rate or message count instantly. Then use those numbers in your reporting.
When It Fits, When It Doesn't
Use this MCP if your core problem is translating large volumes of internal, unstructured text (like web pages and PDFs) into reliable, conversational answers while also needing to track performance metrics. It’s ideal for support teams that need to prove ROI on their AI investments by tracking leads and resolution rates. Don't use it if you simply need a chat widget without the ability to train the bot; in that case, a simple API connection might suffice. Also, don't rely solely on send_message for data—always pair testing with calls like get_bot_analytics so you know how well it performs under simulated load.
Common Questions About Botsonic MCP
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.