CHATFLY MCP. Train, test, and monitor your custom bots.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
CHATFLY manages your custom AI chatbots and knowledge bases. Train bots on internal documents, monitor conversations, and manage bot performance directly from your preferred agent client.
What your AI agents can do
Get chatbot details
Gets detailed information about one specific chatbot.
Get chatfly account info
Retrieves core account and quota usage data.
Get conversation history
Pulls the full message history for a specific chat session.
List all active chatbots in your account or pull detailed specs for a single bot.
See every file uploaded to the knowledge base and trigger retraining when source data changes.
Pull recent chat summaries or retrieve the full, message-by-message history of any conversation.
Send test messages to a bot and receive an immediate, AI-generated response.
Retrieve core account information so you can track your usage quotas at a glance.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
CHATFLY: 8 Tools for Bot Management
These tools let you list all chatbots, track conversations, upload documents, trigger training, and send test messages to your specialized AI bots.
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 CHATFLY on Vinkius019d756dget chatbot details
Gets detailed information about one specific chatbot.
019d756dget chatfly account info
Retrieves core account and quota usage data.
019d756dget conversation history
Pulls the full message history for a specific chat session.
019d756dlist chatfly bots
Lists all custom AI chatbots you have set up in your account.
019d756dlist fly conversations
Retrieves a list of recent chat sessions.
019d756dlist uploaded documents
Shows all documents currently used by the bot's knowledge base.
019d756dsend bot message
Sends a test message to a chatbot and gets an instant reply back.
019d756dtrigger bot training
Starts the process of retraining a chatbot using new knowledge base data.
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 CHATFLY, 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 CHATFLY. 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 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Reviewing bot performance means jumping through dashboards.
Today, if you want to know how your support bots are doing, you have to log into the CHATFLY dashboard. You check the 'Conversations' tab for recent chats, then switch tabs to manually list uploaded documents, and finally click a button somewhere else to start retraining it because one policy changed.
With this MCP, that manual process disappears. Your agent handles all of it in sequence. Need context? Use `get_conversation_history`. Want the bot updated on the latest policies? You check with `list_uploaded_documents` and run `trigger_bot_training`—all through your chat interface.
Getting live insights using send_bot_message
Instead of having to ask a teammate, 'Can you check how the bot handles this scenario?', you just run `send_bot_message`. The agent sends the test prompt and receives the AI's response immediately—no waiting for internal team member availability.
Now you can validate complex user journeys instantly. You don't have to rely on screenshots or manual testing; you get a verifiable, real-time output straight into your workflow.
What you can do with this MCP connector
You use this MCP to take full control of specialized chatbot workflows using your own business data. Instead of building a whole separate dashboard just to check your bots, you connect CHATFLY to any AI agent and manage everything through natural conversation. You can list all available chatbots or get detailed information for one specific bot.
Need to update the knowledge base? You can list all uploaded documents and then trigger training on new data securely. Want to test how a bot responds? Send messages directly to your bots, getting real-time answers, or retrieve full message histories from past conversations. When you're building complex automations that require checking account limits alongside sending a message, the platform handles it all in one place.
This means when you chain CHATFLY with other services via Vinkius, you don't just run tools; you build complete workflows where every data flow is tracked and audited from start to finish.
019d756d-813d-736b-8c19-f51a480c3f0d 
How CHATFLY MCP Works
- 1 Subscribe to this MCP and enter your unique ChatFly API key, getting the connection authorized in your client.
- 2 Use your agent to list all available bots or pull account information to confirm quotas. This validates the setup.
- 3 Now you can send a message to test a bot, then use other commands to retrieve the conversation history for review.
The bottom line is that you manage complex chatbot operations without ever leaving your agent chat interface.
Who Is CHATFLY MCP For?
Support Managers who spend too much time jumping between CRMs and internal knowledge portals. Content Strategists needing to manually initiate bot retraining every time a document is updated. Product teams that need instant ways to test bot responses before releasing new features.
Reviews customer interactions by pulling full message history and checking general account info to confirm the agent has access to necessary data.
Manages knowledge base documents by listing uploaded files and triggering bot retraining directly through their chat interface.
Tests new chatbot features or complex user flows by sending test messages to a specific bot, verifying the response in real-time.
What Changes When You Connect
- Stop guessing if a bot is trained on new data. Use
list_uploaded_documentsto check the knowledge base files, then runtrigger_bot_trainingwhen you're ready. - Don't manually search old chats for context. Use
get_conversation_historyto retrieve the full message log and feed it back into your agent's current workflow. - Need an overview? Instead of jumping through tabs, use
list_chatfly_botsto see every bot you run, then drill down withget_chatbot_detailsfor specific metrics. - Test user flows instantly. You can send a message using
send_bot_messageand immediately get a live response without needing to open the chatbot dashboard. - Keep an eye on costs. Use
get_chatfly_account_infoanytime to confirm your usage quotas, ensuring you never run out of capacity mid-task.
Real-World Use Cases
Debugging a broken bot response
A Product Manager needs to know why the 'Sales Closer' bot gave bad advice. They first use list_fly_conversations to find the relevant chat, then call get_conversation_history to review every message exchanged before trying to retrain it with a better set of documents using trigger_bot_training.
Onboarding new company policies
A Content Strategist writes a 50-page guide and uploads it. They immediately use list_uploaded_documents to confirm the file, then call trigger_bot_training so that the bot can answer questions about the new policy by sending test queries via send_bot_message.
Reviewing a customer service issue
A Support Manager sees an alert. They use list_chatfly_bots to confirm which bot handled it, then call get_chatbot_details to verify its current status and pull the full conversation log using get_conversation_history.
Checking overall platform capacity
A Business Owner wants to know if they have enough resources for a major campaign. They use get_chatfly_account_info first, and then chain that usage data with other MCPs to predict potential costs across multiple services.
The Tradeoffs
Treating the bot like an API endpoint
Manually calling get_chatbot_details every time you want basic info. This is repetitive and wastes tokens.
→
Remember that your agent can list all bots with list_chatfly_bots, giving you a quick overview before needing to pull deep specs using get_chatbot_details.
Ignoring data sources during updates
Uploading new documents and then forgetting to tell the bot about them, leaving it outdated.
→
Always check what you've added with list_uploaded_documents, and never skip calling trigger_bot_training after adding source material.
Assuming a chat transcript is enough
Just reading the last few messages from a conversation without seeing the whole picture.
→
To get the full context, always use get_conversation_history instead of just looking at recent summaries.
When It Fits, When It Doesn't
Use this MCP if your primary problem is managing the lifecycle and performance of custom AI chatbots. You need to be able to train bots on specific documents, monitor who they are talking to, or test their responses before a user sees them. Don't use it if you just need general chat logging without training capabilities—a simple messaging integration would work better. If your goal is building an automated system that needs to check bot status, then pull conversation data, and then send an alert message using another MCP, this platform makes chaining those three steps reliable because Vinkius handles the entire execution in a secure sandbox.
Common Questions About CHATFLY MCP
How do I check my bot's current status with get_chatbot_details? +
You use get_chatbot_details to pull a detailed profile of a specific chatbot. This lets you see its configuration and readiness status without listing every single bot first.
What is the difference between list_fly_conversations and get_conversation_history? +
Listing conversations with list_fly_conversations only gives you a summary of recent chats. If you need the actual text, every message exchange, you have to use get_conversation_history.
Can I train my bot without changing documents first? +
No. You must confirm what data is available by running list_uploaded_documents. After confirming the source material, you run trigger_bot_training to start the process.
Is get_chatfly_account_info useful for billing? +
Yes. This tool retrieves core account and quota information. It's how you check your usage limits before running high-volume tests or automating processes.
If I need to check my usage limits, how do I use get_chatfly_account_info? +
It immediately returns your account quota and usage statistics. This lets you monitor resource consumption for every AI agent connecting through the MCP.
How does list_uploaded_documents help me understand my knowledge base sources? +
This tool pulls a complete inventory of all documents available for training. You can check if the correct data files are linked before triggering any retraining cycles.
What happens when I run trigger_bot_training? Does it start immediately? +
The call initiates the background training process for your chatbot. You'll need to use get_chatbot_details later to monitor the status until training is complete.
Can I find out what conversations happened before running send_bot_message? +
Yes, you should first run list_fly_conversations. This gives you an overview of recent chats, and then get_conversation_history lets you pull the full message thread for review.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.