How to Use the Elasticsearch Vector MCP in Mastra AI

Q: How do I integrate Elasticsearch Vector with a Mastra AI agent?

Initialize the MCPClient pointing to your Vinkius server URL and fetch the tools using mcpClient.listTools(). You then spread these tools directly into your Mastra agent configuration so it can access the vector index.

Q: Can Mastra AI handle index migrations on Elasticsearch Vector automatically?

Yes, your agent can call listindexes to check the current state, and then use createindex to build a new target index if a schema migration is required.

Q: What happens if an Elasticsearch Vector search query fails during a Mastra AI workflow?

Mastra AI catches the error from the search tool and applies your configured retry policy. This keeps your automated pipelines running even during temporary cluster connectivity drops.

Build resilient, self-healing vector search workflows with Mastra AI and your Elasticsearch Vector cluster.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elasticsearch Vector MCP to Mastra AI

Create your Vinkius account to connect Elasticsearch Vector to Mastra AI 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 Elasticsearch Vector with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated vector index setup in Mastra AI workflows

Executing the `create_index` tool lets your Mastra AI agent establish dense vector stores as a step in your automated workflows. This MCP connection handles the heavy lifting. By combining `list_indexes` and `get_index`, the agent verifies the target index exists before running any migrations. If the cluster is offline, Mastra's built-in retry logic backs off and tries again automatically.

Reliable document indexing with auto-retry

Sending embeddings via the `index_document` tool writes high-dimensional embeddings directly to your Elasticsearch cluster. When your ingestion pipeline processes new content, this tool ensures the vector and its metadata are stored correctly. If the write fails due to network hiccups, Mastra AI uses its exponential backoff to retry the `index_document` call. This keeps your MCP workflow completely reliable.

Conditional branching on vector search results

Running the `search` tool executes kNN queries to find similar documents based on your input embeddings. Your agent can read the scores of these matches and branch its logic depending on the confidence level of the results. If the search yields no high-confidence matches, your Mastra workflow can trigger a fallback action. When stale records are found, the agent uses `delete_document` to prune them from the index.

Setup guide

Set up Elasticsearch Vector MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Elasticsearch Vector tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "elasticsearch-vector-mcp-client",
  servers: {
    "elasticsearch-vector-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Elasticsearch Vector Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Elasticsearch Vector tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Elasticsearch Vector transactions"
);
console.log(result.text);

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 Elasticsearch Vector. 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 Elasticsearch Vector 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 Elasticsearch Vector MCP in Mastra AI

Initialize the `MCPClient` pointing to your Vinkius server URL and fetch the tools using `mcpClient.listTools()`. You then spread these tools directly into your Mastra agent configuration so it can access the vector index.

Yes, your agent can call `list_indexes` to check the current state, and then use `create_index` to build a new target index if a schema migration is required.

Mastra AI catches the error from the `search` tool and applies your configured retry policy. This keeps your automated pipelines running even during temporary cluster connectivity drops.

You can filter the tools array before passing it to your agent. This lets you restrict an agent to only run the `search` tool while preventing it from calling destructive tools like `delete_document`.

Your raw embedding documents and dense vectors are transmitted over secure, ephemeral connections. Vinkius executes the MCP Server within a zero-trust sandbox, meaning your index mappings and vector data are never stored or logged on our infrastructure.

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