CHATFLY MCP. Manage custom bots and knowledge bases from your chat client.
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 proprietary data and monitor conversations directly through any AI agent.
Use CHATFLY to list, train, and send messages to your custom bots, keeping all interactions and data sources visible from a single client.
What your AI agents can do
Get chatbot details
Retrieves specific operational details for a single named chatbot.
Get chatfly account info
Gets core account data and monitors your AI usage quotas.
Get conversation history
Retrieves the full message exchange history for a specific chat session.
You can list every custom chatbot you own and get detailed specs for any specific bot using list_chatfly_bots and get_chatbot_details.
You can list all documents uploaded to the knowledge base using list_uploaded_documents to verify the source material for bot training.
You can manually start the training process for a chatbot using trigger_bot_training whenever new data arrives.
You can send test messages to any bot and receive the AI's real-time response using send_bot_message.
You can pull recent chat logs with list_fly_conversations or get the full, detailed message history for a specific chat using get_conversation_history.
You can retrieve your core account information and current usage quotas with get_chatfly_account_info.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
CHATFLY MCP Server: 8 Tools for Bot & Knowledge Management
Use these eight tools to manage the entire lifecycle of your custom AI bots, from training data upload to real-time conversation monitoring.
019d756dget chatbot details
Retrieves specific operational details for a single named chatbot.
019d756dget chatfly account info
Gets core account data and monitors your AI usage quotas.
019d756dget conversation history
Retrieves the full message exchange history for a specific chat session.
019d756dlist chatfly bots
Lists all active custom AI chatbots currently configured in your account.
019d756dlist fly conversations
Lists the most recent chat conversations that took place with your bots.
019d756dlist uploaded documents
Lists all files and documents currently stored in the knowledge base for training.
019d756dsend bot message
Sends a test message to a bot and returns the AI's generated response.
019d756dtrigger bot training
Initiates the data ingestion and training process for a specified 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 CHATFLY, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
CHATFLY MCP Server - Manage Bots and Knowledge Bases
Connect your AI client to CHATFLY to manage your custom chatbots and knowledge bases. You'll list every bot you own and get its specific operational details using list_chatfly_bots and get_chatbot_details. You can check out all the files you uploaded for training by running list_uploaded_documents. You manually start the training process for a bot when new data comes in with trigger_bot_training.
You can send a test message to any bot using send_bot_message and get the bot's real-time answer. To see recent chats, use list_fly_conversations; for the full blow-by-blow of a specific chat, use get_conversation_history. You'll get your core account data and monitor your AI usage quotas with get_chatfly_account_info.
How CHATFLY MCP Works
- 1 Subscribe to this server and provide your ChatFly API Key.
- 2 Use your AI client to call the desired tool (e.g.,
list_chatfly_bots). - 3 The server executes the tool, returns the data, and your agent processes the result.
The bottom line is you manage complex bot interactions and data flows without leaving your primary AI client.
Who Is CHATFLY MCP For?
Support Managers, Content Strategists, Product Teams, and Business Owners need this. If you spend time jumping between a chatbot dashboard, a document repository, and a usage tracker, this is for you. It lets you control your AI assets directly from your agent's chat window.
Reviews customer interactions and checks bot performance by running get_conversation_history and list_fly_conversations.
Manages the knowledge base by running list_uploaded_documents and triggering updates using trigger_bot_training.
Tests bot logic and verifies training status by sending test messages via send_bot_message and checking bot details with get_chatbot_details.
Audits the total conversation volume and monitors resource usage by calling get_chatfly_account_info.
What Changes When You Connect
- Full Chatbot Oversight: Use
list_chatfly_botsandget_chatbot_detailsto see every bot you own and its specific status, eliminating the need to open a separate dashboard just to check a bot's readiness. - Immediate Testing: Run
send_bot_messageto simulate live user input. You get the AI's response instantly, letting you test bot logic without committing to a formal deployment cycle. - Data Source Audit: Run
list_uploaded_documentsto confirm exactly what data the bot is trained on. You know your knowledge base contents are visible, preventing accidental training on stale or incorrect files. - Conversation Deep Dive:
get_conversation_historypulls the entire message thread. This lets you audit a specific customer interaction and see exactly where the bot failed or succeeded. - Operational Control:
trigger_bot_traininggives you a direct way to update your bot's knowledge base. You initiate the training cycle right from your chat interface. - Resource Visibility:
get_chatfly_account_infoshows your current AI usage quotas. You track resource consumption and billing limits without logging into the main admin portal.
Real-World Use Cases
The Bot Needs New Info
The Content Strategist realizes the bot needs to know about the new 'Q3 Pricing Guide.' They run list_uploaded_documents to confirm the file is uploaded, then use trigger_bot_training to push the new data into the bot. They then run send_bot_message to confirm the bot can answer questions about the guide.
Debugging a Bad Answer
A Product Team member notices a bot gave a weird answer. They use list_fly_conversations to find the session, then get_conversation_history to see the exact thread. They use get_chatbot_details to check the bot's last training date and determine if an update is needed.
Checking Customer Support Performance
The Support Manager wants to review a complex customer ticket. They use list_chatfly_bots to confirm the bot ID, then get_conversation_history to pull the full log. This lets them review the bot's performance and identify knowledge gaps for the next training cycle.
Monitoring Account Health
A Business Owner wants to know if they are close to hitting their AI usage limit. They simply call get_chatfly_account_info to get immediate quota status. They can then decide if a training run is worth the cost.
The Tradeoffs
Relying on Dashboard Widgets
Having to navigate to the CHATFLY dashboard, click 'Training', select the bot, click 'Start', and wait for a status update.
→
Just use the trigger_bot_training tool. You initiate the entire process directly from your agent's chat window. It's faster and keeps your workflow linear.
Manual Data Verification
Manually checking if a document was successfully ingested into the knowledge base by looking at a separate file list.
→
Call list_uploaded_documents first. This confirms the file is in the system. Then, use get_chatbot_details to verify the bot has linked to it.
Testing in Production Chat
Asking a real customer a question to test the bot's response, which is risky and slows down support.
→
Use send_bot_message with a test query. You get an immediate, isolated response without impacting actual customer conversations.
When It Fits, When It Doesn't
Use this server if you need to manage the entire lifecycle of a custom chatbot—from data ingestion and training to live conversation monitoring—all from a single prompt. The key is that you need to control the state of the bot.
Don't use this if your only need is to read a static document or integrate with a totally separate system (like a CRM). For simple read-only data, another document-retrieval tool might suffice. But if you need to trigger action (like trigger_bot_training) or test responses (send_bot_message), this is your toolset.
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.
Available Capabilities
Juggling Dashboards to Manage Bot Knowledge
Today, updating a bot's knowledge requires jumping between at least three interfaces: the main dashboard to find the bot, the document repository to upload files, and a separate training tab to hit the 'Start' button. You copy a document link, paste it into the repo, and then manually navigate to the bot settings to trigger the training run. It's a multi-step, copy-paste nightmare.
With the CHATFLY MCP Server, you run a single command. You list the documents with `list_uploaded_documents` and trigger the training with `trigger_bot_training`—all from your agent. You get immediate confirmation that the data is being ingested, and you can immediately test the new knowledge using `send_bot_message`.
Live Bot Testing with send_bot_message
Previously, testing a bot meant going through the bot's native web chat interface. You'd have to manually type in a query, wait for the response, and then copy that output to your analysis sheet. This process was slow and lacked context.
Now, you just use `send_bot_message`. Your agent sends the query, and the server returns the full, structured response right in your chat window. You get immediate, verifiable test results without leaving your workflow.
Common Questions About CHATFLY MCP
How do I list all my chatbots using the CHATFLY MCP Server? +
Run the list_chatfly_bots tool. This immediately returns a list of every custom bot ID and name you have configured in your account.
Does `get_conversation_history` retrieve all chats forever? +
No. This tool retrieves the message history for a specific, identified conversation. You must provide the correct conversation ID to get the full thread.
Can I force a bot to retrain using the CHATFLY MCP Server? +
Yes. You use the trigger_bot_training tool. This initiates the data ingestion process for a specified bot using the current knowledge base.
What information does `get_chatfly_account_info` provide? +
This tool gives you core account details, including vital information about your current AI usage quotas and limits.
How do I test a bot response using the CHATFLY MCP Server? +
Use the send_bot_message tool. This sends a message to a specified bot and returns the AI's generated answer in real time for testing purposes.
How do I check which documents are available for training using `list_uploaded_documents`? +
The list_uploaded_documents tool shows every file in your knowledge base. This helps you track exactly what data the chatbot has access to for its responses.
What is the process for managing multiple chatbots using `list_chatfly_bots`? +
The list_chatfly_bots tool provides a comprehensive list of all your active bots. You can use this list to confirm the names and statuses of every chatbot you've created.
Can I send a message to a specific bot using `send_bot_message`? +
Yes, send_bot_message lets you send a test message to any bot. You get a real-time AI-generated response back, letting you test the bot's performance immediately.
Can I train my bot on a new PDF file through the agent? +
You can trigger the training process using the trigger_bot_training tool once you have added files via the ChatFly dashboard. Future updates will support direct file uploads.
How do I see the history of a specific conversation? +
Use the get_conversation_history tool with the unique conversation ID. Your agent will fetch the full transcript of messages between the user and the bot.
Where do I find my ChatFly API Key? +
Log in to your ChatFly dashboard and navigate to the 'API' or 'Integrations' section. You can generate and copy your API key from there.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Sendbird
Manage Sendbird chat infrastructure — orchestrate users, channels, and moderation directly from your AI agent.
Howuku
Analyze user behavior via Howuku — track projects, recordings, and heatmaps.
Texter
Send automated text messages and run SMS drip campaigns that engage leads and customers with timely follow-ups.
You might also like
Text Readability Scorer
Calculate mathematically accurate readability metrics (Flesch-Kincaid, Gunning Fog, SMOG) for any text. Stop relying on AI 'feelings' — get exact US grade levels for SEO and compliance.
Aimtell
Web push notification orchestration — manage campaigns, segments, and subscribers via AI.
Automate.io
Manage Automate.io workflows seamlessly — audit your bots, connections, and execution runs directly from your AI agent.