Aidbase MCP. Manage support knowledge, chatbots, and inboxes via AI chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Aidbase MCP Server connects your AI agent to your customer support knowledge base and ticketing system. It lets you programmatically list chatbots, inject new FAQs, ingest entire websites, and manage email inboxes with a single conversation.
You get full control over your automated support workflows, treating your AI agent like a dedicated knowledge architect.
What your AI agents can do
Add aidbase faq item
Adds a specific Question and Answer pair to the knowledge base.
Add aidbase website knowledge
Ingests an entire website URL into the knowledge base for AI training.
Check aidbase status
Retrieves the current API operational status of the Aidbase account.
List all active chatbots and retrieve their detailed metadata.
Inject new FAQs or entire websites into the global knowledge base.
Send test messages to a specific chatbot and retrieve its response.
Access and list automated email responders and their associated knowledge bases.
Verify the API connectivity and retrieve current account status metrics.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Aidbase MCP Server: 11 Tools for Support Automation
Use these tools to programmatically manage chatbot configurations, ingest knowledge, test live conversations, and monitor support systems.
019dd0b5add aidbase faq item
Adds a specific Question and Answer pair to the knowledge base.
019dd0b5add aidbase website knowledge
Ingests an entire website URL into the knowledge base for AI training.
019dd0b5check aidbase status
Retrieves the current API operational status of the Aidbase account.
019dd0b5get aidbase chatbot
Retrieves detailed information and metadata for a specific configured chatbot.
019dd0b5get aidbase inbox
Retrieves details and contents of an automated email response inbox.
019dd0b5list aidbase chatbot knowledge
Lists all the knowledge items currently associated with the chatbots.
019dd0b5list aidbase chatbots
Lists all active chatbots configured within the Aidbase account.
019dd0b5list aidbase inbox knowledge
Lists all knowledge items tied to the email inboxes.
019dd0b5list aidbase inboxes
Lists all configured automated email response inboxes.
019dd0b5list aidbase knowledge
Lists every single knowledge item stored in the global knowledge base.
019dd0b5send aidbase reply
Sends a test message to a specific chatbot for immediate response testing.
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 Aidbase, 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
The Aidbase MCP Server connects your AI agent to your support knowledge base and ticketing system. It gives your agent the power to list chatbots, inject new FAQs, ingest whole websites, and manage email inboxes all through a single conversation. You'll get full control over your automated support workflows, treating your agent like a dedicated knowledge architect.
Manage Chatbot Inventory: You can list all active chatbots using list_aidbase_chatbots, and you can pull detailed information and metadata for a specific bot using get_aidbase_chatbot.
Update Knowledge Sources: You'll inject new FAQs into the knowledge base with add_aidbase_faq_item, and you can train the AI on entire websites by passing a URL to add_aidbase_website_knowledge. You can also check every single piece of data stored globally using list_aidbase_knowledge.
Simulate Chat Interactions: You can test a bot's performance by sending a test message to it using send_aidbase_reply. You can also list all knowledge items tied to the chatbots using list_aidbase_chatbot_knowledge.
Review Email Automation: You can access and list all configured automated email response inboxes with list_aidbase_inboxes, and you can check the knowledge associated with those inboxes using list_aidbase_inbox_knowledge. You can also pull the actual contents and details of an inbox using get_aidbase_inbox.
System Health Check: Your agent verifies the API connectivity and pulls current account status metrics using check_aidbase_status.
Manage Inbox Knowledge: You can list all knowledge items tied to the email inboxes using list_aidbase_inbox_knowledge.
How Aidbase MCP Works
- 1 Subscribe to the Aidbase MCP Server and retrieve your API Key from the Aidbase dashboard.
- 2 Instruct your AI client to use a specific tool, like
list_aidbase_chatbotsoradd_aidbase_faq_item. - 3 The agent executes the tool, and you receive the structured data (e.g., list of bots, updated knowledge status) directly in your conversation.
The bottom line is, your AI client acts as a single interface to run all your support intelligence tasks, eliminating manual logins to multiple support tools.
Who Is Aidbase MCP For?
This is for the Customer Support Lead who has to manually update FAQs across three different systems. It's for the Product Manager who needs to verify chatbot responses without leaving their main workspace. And it's for the Developer building custom internal tools who needs reliable, high-speed access to support data.
Uses add_aidbase_faq_item to quickly push fresh documentation to the knowledge base, or list_aidbase_chatbots to see which bots need updates.
Runs get_aidbase_chatbot and send_aidbase_reply to monitor chatbot interactions and verify responder accuracy against live customer data.
Integrates get_aidbase_inbox and list_aidbase_knowledge to pull support data into custom internal tools or scripts.
What Changes When You Connect
- Keep knowledge current with
add_aidbase_website_knowledge. Instead of manually updating dozens of support pages, you push a new URL, and the AI indexes the content automatically. - Test chatbot performance instantly. Use
send_aidbase_replyto send a sample query to a specific bot and get a real-time response, all without leaving your agent interface. - Centralize support visibility.
list_aidbase_chatbotslets you see every bot you run and check its configuration details withget_aidbase_chatbot—all in one query. - Handle email support programmatically.
get_aidbase_inboxlets you monitor automated email responses and confirm that the right knowledge base is attached to the context. - Improve system reliability. Run
check_aidbase_statusto verify API connectivity and get immediate performance reports, so you never guess if your support layer is down. - Save time on data management.
list_aidbase_knowledgeshows you every single piece of data in the global knowledge base, letting you audit what the AI actually knows.
Real-World Use Cases
Onboarding a new product line
A product manager needs the AI to know about a new widget. Instead of writing a dozen new FAQs, they run add_aidbase_website_knowledge with the new product docs URL. The AI agent handles the ingestion, and the chatbots instantly know about the widget.
Verifying a bot's accuracy
A support lead suspects 'Bot X' is giving outdated refund info. They use send_aidbase_reply to send a test query ('What is the refund window?'). The agent captures the response, allowing the lead to immediately verify the bot's accuracy.
Auditing email support context
An ops engineer notices some emails are missing context. They run list_aidbase_inboxes and then list_aidbase_inbox_knowledge to check which knowledge is assigned to which email responder, ensuring full context application.
Checking global system health
The development team gets a 'Support down' alert. Instead of calling three different APIs, they run check_aidbase_status. The agent provides a single, unified status report, telling them exactly where the system is failing.
The Tradeoffs
Manual Portal Juggling
Logging into the support portal to update FAQs, then switching to the bot dashboard to check logs, and finally logging into the email system to confirm context. It takes 15 minutes and requires 3 passwords.
→
Use the MCP Server to keep everything in one place. Run add_aidbase_faq_item for the FAQ, then list_aidbase_chatbots to see the bot, and finally send_aidbase_reply to test it. It’s all in the agent chat.
Assuming Knowledge Sync
Thinking that because you added a new document to Google Drive, the chatbot instantly knows about it. This leads to customer frustration because the knowledge gap isn't closed.
→
You must explicitly tell the server to update the knowledge. Use add_aidbase_website_knowledge with the URL. The agent handles the ingestion and updates the bot when it's done.
Testing without Records
Just sending a message to a chatbot and assuming the interaction is logged. If the session ID is needed later, you're out of luck.
→
Use send_aidbase_reply to send the test message. The agent captures the response and logs the session ID, giving you a traceable record of the interaction.
When It Fits, When It Doesn't
Use this server if your primary pain point is managing multiple, separate support data sources (FAQs, websites, email inboxes) and you need to keep them all synchronized with a single AI agent. You need the ability to programmatically push new data or test live interactions without leaving your chat window. Don't use it if you just need a single, simple API call to fetch a user's name; use a generic data lookup tool instead. If your core need is managing structured data within the knowledge base, start with list_aidbase_knowledge. If you need to test the AI's output, send_aidbase_reply is your tool. If you need to audit the system health, run check_aidbase_status.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Aidbase. 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 11 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Updating support documentation shouldn't require 15 clicks.
Right now, adding a new FAQ means logging into the support portal, finding the right section, typing the Q&A, and hitting save. If you have 50 FAQs to update, you're copy-pasting and clicking for an hour. It's slow, and you always forget to update one section.
With this MCP server, you just ask your agent to update the knowledge. You use `add_aidbase_faq_item` or `add_aidbase_website_knowledge`. The agent runs the tool, handles the data ingestion, and confirms the knowledge is pushed to the AI. Done.
Aidbase MCP Server: Manage support knowledge and chatbots.
Previously, checking a bot's performance meant jumping between the bot dashboard, the knowledge base audit log, and the email responder logs. It was a mess of disconnected screens, and you never got a full picture of the system's health.
Now, your agent handles it all. You can run `list_aidbase_chatbots` to see what's running, `list_aidbase_knowledge` to see what it knows, and `check_aidbase_status` to confirm everything is green. It gives you a single source of truth.
Common Questions About Aidbase MCP
How do I use the `add_aidbase_website_knowledge` tool? +
You provide the full URL to the webpage you want the AI to know about. The agent initiates the knowledge ingestion process, and Aidbase starts indexing the content. Wait for the confirmation that the content is successfully indexed.
What is the purpose of the `send_aidbase_reply` tool? +
This tool lets you send a test message to a specific chatbot. It runs the conversation and returns the chatbot's response, giving you a record of the interaction for testing purposes.
How do I list all my chatbots with `list_aidbase_chatbots`? +
Simply ask the agent to run list_aidbase_chatbots. It returns a list of all configured chatbots, including their unique IDs and status.
Can I check the system health with `check_aidbase_status`? +
Yes. Running check_aidbase_status queries the API and returns the current account status. This confirms the connection is active and provides instant performance reporting.
Does `list_aidbase_knowledge` show all data? +
Yes, list_aidbase_knowledge lists every single knowledge item across the entire global knowledge base, providing a complete audit trail of the AI's knowledge.
How do I manage email responders using the `list_aidbase_inboxes` tool? +
This tool retrieves a list of your configured email AI inboxes. You can use this list to identify which automated responders are active and what knowledge bases they are assigned to.
What details can I get about a specific chatbot using `get_aidbase_chatbot`? +
The get_aidbase_chatbot tool returns detailed metadata for a given chatbot. This includes its configuration settings, current knowledge sources, and performance metrics.
If I want to update my FAQs, should I use `add_aidbase_faq_item` or `add_aidbase_website_knowledge`? +
Use add_aidbase_faq_item for single, specific Question/Answer pairs. Use add_aidbase_website_knowledge when you need to index an entire website or a large set of URLs.
How do I find my Aidbase API Key? +
Log in to your account, navigate to Settings > API Keys, and generate a new key for your integration.
Can I test bot responses via AI? +
Yes! The send_aidbase_reply tool allows your agent to interact with specific bots and retrieve high-fidelity AI responses programmatically.
How do I teach the AI a new URL? +
Use the add_aidbase_website_knowledge tool and provide the target URL. Aidbase will automatically crawl and index the content for your bots.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Egnyte
Store and govern enterprise content with intelligent file management, access controls, and compliance monitoring across teams.
The Botforge
Deploy custom AI chatbots for enterprise customer support with multilingual capability and deep integration into your tech stack.
Circle.so
Manage online communities via Circle — track members, monitor posts, and manage spaces directly from any AI agent.
You might also like
Make.com Webhook Trigger
This MCP does exactly one thing: it sends JSON payloads to Make.com Webhooks. That's its only function. Incredible for connecting AI agents to thousands of visual automation workflows instantly.
QStash (Serverless Message Queue)
Manage serverless messaging, task scheduling, and webhooks via Upstash QStash — publish messages, manage queues, and handle DLQs directly.
TomTom Parking Availability
Search parking spots — audit locations and availability via AI.