How to Use the Aidbase MCP in Claude Code

Q: Can I sync my Aidbase knowledge base from a CI pipeline with Claude Code?

Yes. In your deployment script, just add a command to call addaidbasewebsiteknowledge with the URL of your updated docs. It's a single line in your CI configuration file.

Q: How do I check if the Aidbase API is online from my terminal?

Just run claude mcp exec aidbase-mcp -- checkaidbasestatus. You'll get an immediate status check, which is perfect for automated health checks in monitoring scripts.

Pipe your Aidbase support data into any script or command-line tool using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aidbase MCP to Claude Code

Create your Vinkius account to connect Aidbase to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Aidbase with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate KB deployments in your CI/CD pipeline

This is what a real DevOps workflow looks like. Add a step to your GitHub Action that calls Claude Code with `add_aidbase_website_knowledge` whenever your main docs site is deployed. Your knowledge base will always be in sync with your public-facing documentation, with zero manual work. You can also use `list_aidbase_knowledge` to get a manifest of all current items. Pipe that to a file, commit it, and now you have a versioned history of your KB content right in git.

Script your Aidbase monitoring from the terminal

This MCP Server is built for the command line. Write a simple shell script that calls `check_aidbase_status` and sends an alert if it fails. Set up a cron job to run `list_aidbase_inboxes` and `list_aidbase_chatbots` to generate a daily report on all your active support assets. The output is clean text, so you can pipe it to anything. Use `grep` to find a specific chatbot, `jq` to parse details, or `awk` to format a custom report. It's just another command-line tool in your arsenal.

Export support data for backups and analysis

Claude Code makes it simple to pull data out of Aidbase. You can write a script that calls `list_aidbase_chatbots`, then loops through each bot and uses `list_aidbase_chatbot_knowledge` to get all its associated content. Pipe the output to a JSON file, and you've got a clean backup. You can also feed this data into other scripts for analysis. It's a straightforward way to get your data out of the platform and into your own environment.

Setup guide

Set up Aidbase MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see aidbase-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Aidbase transactions." It will automatically discover and invoke the available Aidbase tools.

Terminal

claude mcp add --transport http aidbase-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Aidbase MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "aidbase-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Aidbase now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Aidbase MCP in Claude Code

You call Claude Code with the tool name and arguments, just like any other CLI command. For example: `claude mcp exec aidbase-mcp -- list_aidbase_chatbots | jq .`. The output is piped to standard out.

Yes. In your deployment script, just add a command to call `add_aidbase_website_knowledge` with the URL of your updated docs. It's a single line in your CI configuration file.

You can list and get details for chatbots, inboxes, and knowledge base items. The output is structured JSON, so it's easy to parse with tools like `jq` or in any scripting language.

Just run `claude mcp exec aidbase-mcp -- check_aidbase_status`. You'll get an immediate status check, which is perfect for automated health checks in monitoring scripts.

Your data, such as chatbot configurations or knowledge base content, is streamed through a sandboxed, memory-only environment for each command. Vinkius never writes your data to disk, and the connection is secured end-to-end. Once the command finishes, the environment is destroyed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript