How to Use the Cognita (RAG Framework) MCP in Mastra AI

Q: How do I handle RAG query retries using Mastra AI and Cognita (RAG Framework)?

You map the ragquery tool to a Mastra workflow step. If the Cognita endpoint experiences a transient error, Mastra's built-in engine automatically retries the tool call using your configured exponential backoff settings.

Q: How does Mastra AI manage Cognita (RAG Framework) tool approvals?

You can enable the requireToolApproval flag in Mastra for sensitive tools like ingestdata. This pauses the workflow and requires a human operator to approve the JSON payload before it alters your active RAG buckets.

Q: How do I register the Cognita tools with a Mastra agent?

You initialize the client using the @mastra/mcp package, call listTools(), and spread those tools directly into your Mastra agent's tool array. The framework automatically handles the underlying transport protocol.

Q: How does this MCP Server protect my Cloud logging traces and payloads?

Every trace log and payload ID processed via getcollection is isolated inside ephemeral Vinkius sandboxes. No RAG data is cached or stored on the proxy layer, ensuring strict end-to-end data privacy for your enterprise workflows.

Build resilient, self-healing RAG workflows with Mastra AI and the Cognita (RAG Framework) MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognita (RAG Framework) MCP to Mastra AI

Create your Vinkius account to connect Cognita (RAG Framework) 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 Cognita (RAG Framework) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient RAG workflows with Mastra AI

The `rag_query` tool integrates directly into Mastra AI's conditional branching engine to handle vector search failures gracefully. If a RAG query fails due to rented transformation vector timeouts, Mastra automatically retries the operation with exponential backoff before notifying your admin. You can feed the output of `search_chunks` into subsequent workflow steps to dynamically adjust your search presets. This ensures your autonomous agent always works with valid, cached rules even when network conditions degrade.

Automated JSON ingestion pipelines

The `ingest_data` tool lets Mastra AI agents automatically provision highly-available JSON payloads and set up new resource directories during background runs. If an ingestion step fails, the built-in workflow engine retries the process without crashing your main application thread. While that agent runs, the MCP Server provides explicit cloud logging traces via `get_collection`. This gives your Mastra workflows full visibility into payload IDs and execution paths without manual debugging.

Dynamic model routing in Mastra agents

The `list_models` tool inspects deep internal arrays within Cognita to mitigate specific picture constraints inside your Mastra AI agents. Your agents can query this tool to decide which LLM is best suited for the current RAG context before executing a search. Combine this with `list_data_sources` to let your workflow automatically extract active bucket structural properties. That's how the agent decides whether to route the query to a hot bucket or trigger a new ingestion workflow.

Setup guide

Set up Cognita (RAG Framework) 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 Cognita (RAG Framework) 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: "cognita-rag-framework-mcp-client",
  servers: {
    "cognita-rag-framework-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Cognita (RAG Framework) 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 Cognita. 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 Cognita (RAG Framework) 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 Cognita (RAG Framework) MCP in Mastra AI

You map the `rag_query` tool to a Mastra workflow step. If the Cognita endpoint experiences a transient error, Mastra's built-in engine automatically retries the tool call using your configured exponential backoff settings.

Yes, you can configure a Mastra workflow trigger that calls `ingest_data` whenever a new file is detected. The workflow handles the JSON payload provisioning and directory generation entirely in the background.

You can enable the `requireToolApproval` flag in Mastra for sensitive tools like `ingest_data`. This pauses the workflow and requires a human operator to approve the JSON payload before it alters your active RAG buckets.

You initialize the client using the `@mastra/mcp` package, call `listTools()`, and spread those tools directly into your Mastra agent's tool array. The framework automatically handles the underlying transport protocol.

Every trace log and payload ID processed via `get_collection` is isolated inside ephemeral Vinkius sandboxes. No RAG data is cached or stored on the proxy layer, ensuring strict end-to-end data privacy for your enterprise workflows.

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