How to Use the Marqo AI (Vector Search & Embeddings) MCP in Claude Code

Q: How do I pipe data to the Marqo tools using Claude Code?

You can pipe JSON directly. For example: cat documents.json claude mcp call marqo adddocuments. Claude Code reads from stdin and uses it as the input for the tool.

Q: Is my data secure when I use the Marqo AI (Vector Search & Embeddings) server from a script with Claude Code?

Yes. When your script calls tools like adddocuments, the payload is sent over a secure connection to a single-use, sandboxed Vinkius instance. The MCP server only holds your data—like document content and IDs—in memory for the duration of that API call. Nothing is logged or stored.

Run Marqo AI tensor search and index management from your terminal. Perfect for CI/CD and backend scripts with 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 Marqo AI (Vector Search & Embeddings) MCP to Claude Code

Create your Vinkius account to connect Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Indexing for Automation

Build and populate Marqo indexes without leaving the command line. Use `create_index` in a bash script to provision new vector spaces as part of your deployment process. Then, pipe a JSONL file of your records to a script that calls `add_documents`. It's built for automation. Run it in a cron job to keep your search index fresh or as a step in a data processing workflow.

Tensor Search from the Terminal

This MCP server puts Marqo's `tensor_search` right at your fingertips. Run a search and pipe the JSON output directly to `jq` for filtering or to another script for processing. This is how you build backend services. Your application's API can call a simple shell script that executes a `tensor_search` through Claude Code, gets the results, and returns them. No complex SDKs required.

Automate Index Auditing in CI/CD

Keep your search infrastructure in check automatically. Add a step to your CI pipeline that runs `list_indexes` and `get_index_stats` to verify your indices are configured correctly after every deployment. If the document count from `get_index_stats` is lower than expected, you can fail the build. You can also write a cleanup job that uses `delete_documents` to periodically prune old records, all managed through this MCP connection.

Setup guide

Set up Marqo AI (Vector Search & Embeddings) 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 marqo-ai-vector-search-embeddings-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Marqo AI (Vector Search & Embeddings) transactions." It will automatically discover and invoke the available Marqo AI (Vector Search & Embeddings) tools.

Terminal

claude mcp add --transport http marqo-ai-vector-search-embeddings-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 Marqo AI (Vector Search & Embeddings) 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": {
    "marqo-ai-vector-search-embeddings-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 Marqo AI. 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) MCP in Claude Code

You can pipe JSON directly. For example: `cat documents.json | claude mcp call marqo add_documents`. Claude Code reads from stdin and uses it as the input for the tool.

Yes, that's a primary use case. Install Claude Code in your Docker image, configure the MCP connection, and you can run `tensor_search` or `add_documents` as part of any containerized task.

Store your Vinkius MCP token in your CI/CD platform's secrets manager (like GitHub Actions Secrets). Then, expose it as an environment variable that your script uses to configure Claude Code at runtime. Don't hardcode it.

Write a shell script that first fetches new data, then calls `delete_documents` for stale IDs, and finally pipes the new data to `add_documents`. Run this script as a nightly cron job. You can check the result with `get_index_stats`.

Yes. When your script calls tools like `add_documents`, the payload is sent over a secure connection to a single-use, sandboxed Vinkius instance. The MCP server only holds your data—like document content and IDs—in memory for the duration of that API call. Nothing is logged or stored.

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