Botsonic MCP. Train bots on your data and manage support conversations.
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 manages your entire fleet of custom AI chatbots. Connect this MCP to train bots using internal documentation and websites, manage bot personalities, send messages for real-time responses, and track performance metrics like resolution rates.
It's how you turn static knowledge into active customer support.
What your AI agents can do
Add knowledge url
Adds a specific webpage URL to the bot's knowledge base, allowing it to read and reference that content.
Check botsonic status
Verifies if the connection between your agent and the Botsonic platform is currently active and working.
Create bot
Builds a new, unique chatbot profile with custom instructions and personality settings.
Feeds whole websites or documents into the chatbot's knowledge base so it can answer questions using that material.
Retrieves analytics showing conversation volume, message counts, and resolution rates for monitoring health.
Allows you to list, create, and update multiple distinct chatbots, each with its own personality and instructions.
Fetches the full, message-by-message history for any past chat session on a specific bot.
Gathers all contact information and key details that the chatbot collects from customers during live conversations.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Botsonic: 12 Tools for Bot Management
These tools allow you to build, train, monitor, and troubleshoot every aspect of your customer-facing AI chatbot fleet.
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 specific webpage URL to the bot's knowledge base, allowing it to read and reference that content.
019dd0c4check botsonic status
Verifies if the connection between your agent and the Botsonic platform is currently active and working.
019dd0c4create bot
Builds a new, unique chatbot profile with custom instructions and personality settings.
019dd0c4get bot
Retrieves all current configuration details for a single, specific bot by its ID.
019dd0c4get bot analytics
Pulls detailed performance metrics like conversation volume or average satisfaction score for any deployed bot.
019dd0c4get conversation
Fetches the complete transcript history of a single chat session, including all user and bot messages.
019dd0c4list bots
Shows an inventory list of every chatbot that has been configured in your account.
019dd0c4list conversations
Retrieves a summary list of recent chat sessions across multiple bots for quick review.
019dd0c4list knowledge base
Displays all the sources (URLs, documents) currently used to train and inform your chatbot's responses.
019dd0c4list leads
Gathers a record of every contact or lead captured by any bot during customer interactions.
019dd0c4send message
Sends an immediate prompt to a specific bot and receives the AI-generated response in real time.
019dd0c4update bot
Modifies existing settings, instructions, or knowledge base links for an already running chatbot.
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 endless cycle of dashboards and spreadsheets.
Right now, tracking what your chatbots actually do is a mess. You have to jump from the chat log dashboard to the performance report tab, then into a separate spreadsheet just to pull out all the unique lead emails. If you want to know if a bot changed its tone after an update, you're copying and pasting entire conversation histories just to compare them.
With this MCP, that process disappears. Your agent client handles it all. You use `list_conversations` for a quick overview, then call `get_bot_analytics` to see the metrics change right there in your chat window. It's instant visibility into performance data.
Using get_bot_analytics: Knowing what worked and what didn't.
Before this, figuring out if a new knowledge source helped required manually reviewing hundreds of transcripts to see if the answer changed. You couldn't quantify success; you could only guess.
Now, calling `get_bot_analytics` gives you hard numbers—resolution rates and message counts. You know instantly whether that update actually improved customer outcomes or just added noise.
What you can do with this MCP connector
This connector lets you build, deploy, and monitor sophisticated AI chatbots trained on your own data. You stop managing bots through a separate dashboard and start controlling them right from your preferred agent interface. Need to teach the bot about new product lines? Just add web page URLs—the chatbot ingests that knowledge automatically so it can answer questions immediately.
Running into an issue with customer support flow? Your agent can send messages directly to the bot for real-time responses, and you can even retrieve every lead collected during those chats. When things get complex, Vinkius provides full visibility through its AI Analytics. You always know which tools were called, exactly what data flowed through, and how your budget is being spent—nothing happens in the dark.
This gives product managers and support teams a single source of truth for bot performance across every interaction.
019dd0c5-0374-7287-93b5-958c697c6413 
How Botsonic MCP Works
- 1 Subscribe to this MCP and enter your Botsonic API Token into Vinkius.
- 2 Connect your agent client (Claude, Cursor, etc.) using the single connection point from any compatible application.
- 3 Start calling the available tools—for instance, use
list_botsto see what's running orsend_messageto test a bot.
The bottom line is: you manage your entire chatbot ecosystem through simple API calls exposed by this MCP.
Who Is Botsonic MCP For?
This setup is for the Support Manager who's tired of switching between a CRM, a documentation portal, and a reporting dashboard just to analyze one week's worth of bot performance. It’s for the Product Owner who needs to test new knowledge sources against multiple bot personalities before launch.
Monitors chat conversations in real-time, reviews resolution rates using get_bot_analytics, and ensures bots capture necessary data by reviewing the list of leads.
Tests bot responses against new documentation sources using add_knowledge_url and updates bot instructions via update_bot before a full release.
Manages the knowledge base by listing existing sources (list_knowledge_base) or creating entirely new specialized bots for different product lines using create_bot.
What Changes When You Connect
- Instead of manually checking dashboards, you can use
get_bot_analyticsto pull immediate performance metrics, tracking everything from message count to resolution rate in one API call. - When a customer leaves contact details, you don't lose them. Use
list_leadsto instantly retrieve all captured lead data and analyze it for sales follow-up. - Need the bot trained on new documentation? You can use
add_knowledge_urlto feed fresh content without downtime, ensuring your chatbot always has the latest information. - If a customer asks an unusual question, you don't have to guess. Use
send_messageto send a prompt and see how the bot responds in real-time for testing purposes. - The ability to call tools like
list_botsandget_botlets your agent manage complex deployments, making it easy to audit every chatbot configuration on your platform.
Real-World Use Cases
Auditing Bot Behavior After a Policy Change
The compliance officer suspects the 'Billing Bot' is giving incorrect pricing info. They use get_conversation to pull transcripts from last week, cross-reference them with list_knowledge_base to check if the latest policy documents were indexed properly, and then call update_bot to correct the instructions.
Quickly Scaling Support During Peak Season
The support team needs a specialized bot for Tier 2 hardware issues. They use create_bot, feed it all the engineering manuals using add_knowledge_url, and then immediately start testing with send_message to ensure accuracy before going live.
Identifying High-Value Leads from Chat Logs
A growth marketer wants to find users who talked about enterprise pricing. They run list_leads, filter by keywords, and export the data to see which bots performed best at capturing high-quality prospects.
Checking Bot Health Across Multiple Lines
The technical manager wants a quick overview of all available chatbots. They use list_bots to get an inventory, then call get_bot_analytics for the top three by volume to check their overall health status.
The Tradeoffs
Treating bots like search engines
Just calling a tool to list all knowledge sources (list_knowledge_base) and expecting the AI agent to write a summary report of what they contain.
→
Don't just list the sources. You need to use send_message to ask the bot a specific question, which forces it to actively search and synthesize an answer using the indexed knowledge base.
Manually tracking every single chat transcript
The team logs into the dashboard daily, clicking through dozens of conversations to find key data points.
→
Use list_conversations first for a summary view. If you need deep detail on one specific interaction, then call get_conversation.
Overwriting bot personality accidentally
A developer calls update_bot and only changes the knowledge base URL but forgets to keep the original system instructions, making the bot sound generic.
→
Always retrieve the existing settings first using get_bot. Then, use that data as a template when calling update_bot so you don't accidentally wipe out key personality traits.
When It Fits, When It Doesn't
Use this MCP if your primary need is managing the lifecycle and performance of AI chatbots. You need to train them on proprietary content, track conversations, or capture leads generated through chat interfaces. Don't use it if you need to write directly to external systems—for example, if you need a tool that automatically creates a new record in Salesforce or sends an email outside of the bot conversation flow; for those actions, look for dedicated CRM or messaging MCPs. If your goal is just viewing basic data, remember list_leads gives you the contacts, but get_bot_analytics tells you why they were captured.
Common Questions About Botsonic MCP
How do I train the bot using add_knowledge_url? +
You call add_knowledge_url with the specific web address you want the bot to learn from. The system then crawls that page and indexes the content, making it available for answering questions.
What is the difference between list_conversations and get_conversation? +
list_conversations gives you a summary of recent chats across all bots; get_conversation fetches the full, detailed transcript history for one specific chat session.
Can I use get_bot to see if my bot is still active? +
Yes. You can call get_bot with your bot's ID to pull its current configuration and status details. This confirms the bot is set up correctly before you rely on it.
How do I list all the different chatbots I have made? (list_bots) +
Just call list_bots. It gives you an inventory of every unique chatbot profile—the names, IDs, and basic status for your entire bot fleet.
What does running the `check_botsonic_status` tool confirm about my account? +
It confirms if your API token is valid and that Vinkius can establish a connection to the Botsonic platform. Running this first step verifies connectivity, which saves you time troubleshooting issues before you start building out conversations or training knowledge sources.
What kinds of changes can I make using `update_bot`? +
You can modify a bot's core instructions, adjust its personality profile, or update the linked knowledge base configuration. This allows you to fine-tune the chatbot as your product requirements change without having to create an entire new version.
How do I use `get_bot_analytics` to measure performance? +
This tool pulls key metrics like conversation volume, total message counts, and resolution rate. You can compare these numbers across different bots or time periods to pinpoint where your support process needs improvement.
When I run `list_leads`, what specific data points do I receive for each lead? +
Each listed entry provides the captured contact details, the ID of the bot that collected them, and a summary of their initial inquiry. This lets your team immediately sort through potential leads needing follow-up.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.