# Aidbase MCP MCP

> Aidbase connects your AI clients to automated customer support and knowledge management. It lets you programmatically index entire websites, add specific FAQs, monitor chat performance, and manage email responses using natural conversation.

## Overview
- **Category:** productivity
- **Price:** Free
- **Tags:** aidbase, chatbot-api, knowledge-base-automation, ai-support, email-responder, faq-orchestration, customer-engagement, ai-agent, mcp

## Description

This connector gives your agent full control over complex support workflows. You can treat your chatbot like a dedicated employee: listing all configured bots, pulling detailed metadata, or sending test messages to check its response accuracy. If you need the bot to know new stuff, you don't manually update dashboards; you just point it at new website URLs for ingestion, or use tools to inject specific Q&A items into existing FAQs. You can even monitor automated email responders and verify API connectivity right through your client. It’s all about managing intelligence—from the knowledge graph up to the final reply—all managed within a single flow via Vinkius. Your AI acts as both the support engineer and the knowledge architect, taking over tasks that used to require logging into multiple portals.

## Tools

### add_aidbase_faq_item
Adds a single question and answer pair directly into your knowledge base.

### add_aidbase_website_knowledge
Indexes an entire website URL, making all its content available to the AI.

### check_aidbase_status
Verifies the current operational status and API connectivity for your account.

### get_aidbase_chatbot
Retrieves specific, detailed configuration settings for one chatbot instance.

### get_aidbase_inbox
Gets the current details and status of an automated email responder inbox.

### list_aidbase_chatbot_knowledge
Lists all specific knowledge items indexed for a particular chatbot.

### list_aidbase_chatbots
Retrieves the names and IDs of every chatbot configured in your account.

### list_aidbase_inbox_knowledge
Lists all knowledge assets assigned to a specific email inbox responder.

### list_aidbase_inboxes
Retrieves the IDs and names of every automated email inbox you manage.

### list_aidbase_knowledge
Lists all types of knowledge assets available across your entire system, regardless of source.

### send_aidbase_reply
Sends a direct message to a chatbot and gets the resulting answer for logging or testing purposes.

## Prompt Examples

**Prompt:** 
```
List all configured chatbots in my Aidbase account.
```

**Response:** 
```
I've retrieved your chatbots. You currently have 3 active bots, including 'Support Hero' (ID: bot_123) and 'Lead Qualifier'. Which one should we test or update with new knowledge?
```

**Prompt:** 
```
Add 'https://docs.vinkius.com/faq' to my AI knowledge base.
```

**Response:** 
```
Knowledge ingestion triggered! I've added the FAQ URL to your global knowledge base. Aidbase is now indexing the content. I'll notify you when your bots are updated with this high-fidelity data.
```

**Prompt:** 
```
Send a message to chatbot 'bot_123': 'What is your refund policy?'.
```

**Response:** 
```
Chatbot response received: 'Our refund policy allows for full returns within 30 days of purchase.' I've documented the session ID for your high-fidelity interaction logs.
```

## Capabilities

### List all chatbots
Retrieves a full list of every configured chatbot instance you run.

### Manage knowledge sources
Programmatically indexes new websites or injects specific FAQs into the knowledge base, keeping your AI up-to-date automatically.

### Test chatbot performance
Sends messages to a specified chatbot and retrieves its high-fidelity response, allowing you to test integrations or track conversations.

### Monitor email workflows
Accesses details about your automated email responders and checks which knowledge bases they are assigned to.

### Check system status
Verifies the current API connectivity and retrieves account-level operational reports for instant troubleshooting.

## Use Cases

### The new product launch
A Content Strategist needs the AI chatbot to know about a brand-new feature. Instead of waiting for manual review, they run add_aidbase_website_knowledge on the staging site URL. Within minutes, the bot can answer questions about the new feature.

### Debugging a broken email responder
The ops engineer notices that certain customer emails aren't getting routed correctly. They use list_aidbase_inboxes to confirm which inboxes exist, then get_aidbase_inbox to check the assigned knowledge base for potential misconfigurations.

### Testing a complex conversation path
A Product Manager wants to see how the bot handles refund requests. They use send_aidbase_reply, sending a specific prompt like 'What is your return window?' and capture the response ID for later audit logs.

### Auditing knowledge dependencies
A developer needs to know which bots rely on what data. They first list all chatbots using list_aidbase_chatbots, then run list_aidbase_chatbot_knowledge against each ID to map out the full dependency graph.

## Benefits

- Stop manually updating FAQs. You can use add_aidbase_faq_item to inject new Q&A pairs instantly, keeping the knowledge base current without touching a dashboard.
- Ingest entire sites with one call. Use add_aidbase_website_knowledge when your documentation changes, letting the AI read the whole thing instead of just a few linked pages.
- Verify bot functionality before deployment. You can test specific responses using send_aidbase_reply, logging the exact answer to ensure accuracy for high-stakes interactions.
- Manage email automation centrally. list_aidbase_inboxes lets you see every responder set up, and get_aidbase_chatbot lets you check a bot's full configuration settings in one place.
- Always know your status. Run check_aidbase_status anytime to confirm API connectivity; it’s great for error handling before any big workflow runs.

## How It Works

The bottom line is: your agent handles the API interaction; you just tell it what job needs doing.

1. First, subscribe to this MCP and grab your dedicated API Key from the Aidbase dashboard.
2. Next, give your agent a clear command—like 'list all chatbots' or 'add website knowledge for X URL'.
3. Finally, the system executes the tool call. You get back structured data (e.g., bot IDs, status codes) that you can then pass to another step in your workflow.

## Frequently Asked Questions

**How do I check if my chatbot is connected using list_aidbase_chatbots?**
Use list_aidbase_chatbots to get a full roster of all available bots and their IDs. This confirms the bot exists in your account before you try to interact with it.

**What is the best way to update FAQs? Should I use add_aidbase_faq_item or something else?**
Use add_aidbase_faq_item. This tool is designed for injecting specific, granular knowledge (a single Q&A pair) directly into the system's core knowledge base.

**Can I use get_aidbase_chatbot to see how my bot replies?**
No. Use send_aidbase_reply instead. The get_aidbase_chatbot tool only retrieves the *configuration* settings, not a live conversation or response.

**I need to index an entire department handbook; which tool should I use?**
Use add_aidbase_website_knowledge. This handles large volumes of content by taking a full URL and letting the AI crawl and ingest everything on that site.

**Before I start calling tools like `list_aidbase_chatbots`, how do I verify that my API key has active connectivity using `check_aidbase_status`?**
The tool immediately confirms if your credentials are valid and the service is operational. It provides a real-time status report, letting you know instantly if there's an issue with authentication or external system downtime.

**I want to scope my search; how do I use `list_aidbase_chatbot_knowledge` instead of just listing all knowledge items?**
This tool filters the entire knowledge base down to only what a specific bot knows. It's crucial when you need to verify that a particular chatbot has access to niche or department-specific documentation.

**When using `get_aidbase_inbox`, does it provide the full context of an automated email reply?**
Yes, this tool retrieves detailed information about the AI inbox. It shows not just the message content, but also which specific knowledge bases were applied to generate the response, ensuring perfect context tracking.

**If I send many messages using `send_aidbase_reply` in a short time, should I worry about rate limiting?**
The API enforces usage limits to maintain stability. If you hit a threshold, your agent will receive an error code rather than failing silently, so be sure to implement proper retry logic.