How to Use the Amazon Bedrock KB MCP in Cursor

Q: How does Cursor access my Amazon Bedrock KB documents?

Cursor invokes the retrieve tool to fetch text chunks from your AWS vector index. The editor then injects these chunks directly into the model's system prompt to generate grounded code.

Q: Can I sync my Amazon Bedrock KB directly from Cursor using this MCP Server?

You use listingestionjobs inside Cursor to track whether your data source is finished syncing. This keeps your coding session aligned with the latest document ingestion status in AWS.

Q: How do I switch between different Amazon Bedrock KB targets in Cursor?

Cursor runs listknowledgebases to find all active indexes in your account. You can specify which index ID to target in your chat or let the editor select the correct one based on your open files.

Write code grounded in your AWS Bedrock knowledge bases directly inside your Cursor editor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Bedrock KB MCP to Cursor

Create your Vinkius account to connect Amazon Bedrock KB to Cursor 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 Amazon Bedrock KB with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate code using Amazon Bedrock KB context in Cursor

The `retrieve_and_generate` tool pulls technical specifications from your AWS vector store to guide the code Cursor writes. Instead of guessing API structures, your editor queries your internal documentation using this MCP Server to generate accurate code on the first try. Cursor calls `retrieve` to pull raw Markdown or text specifications directly into the active editor context. This prevents the agent from inventing functions that don't exist in your actual codebase documentation.

Track data ingestion jobs inside your editor

The `list_ingestion_jobs` tool displays the status of your AWS Bedrock sync operations directly in the Cursor terminal panel. When updating local documentation files, it's easy to check if the cloud index has finished processing your changes. By calling `list_data_sources`, Cursor identifies which S3 buckets feed your active knowledge base. This lets you verify that your local workspace changes align with the configured data pipelines.

Inspect Bedrock index details from the Cursor sidebar

The `get_knowledge_base` tool pulls the exact configuration schema of your AWS Bedrock index into Cursor. You can inspect vector dimensions and model mappings without leaving your active file. Using this MCP Server to run `list_knowledge_bases` lets your coding agent discover all available indexes in your AWS account. This allows Cursor to switch between staging and production vector stores dynamically based on your current branch.

Setup guide

Set up Amazon Bedrock KB MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Amazon Bedrock KB MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Amazon Bedrock KB transactions." If the MCP tools are loaded correctly, Cursor will call the Amazon Bedrock KB tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "amazon-bedrock-kb-mcp": {
      "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 Amazon Bedrock. 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 Amazon Bedrock KB 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 Amazon Bedrock KB MCP in Cursor

Cursor invokes the `retrieve` tool to fetch text chunks from your AWS vector index. The editor then injects these chunks directly into the model's system prompt to generate grounded code.

You use `list_ingestion_jobs` inside Cursor to track whether your data source is finished syncing. This keeps your coding session aligned with the latest document ingestion status in AWS.

Cursor runs `list_knowledge_bases` to find all active indexes in your account. You can specify which index ID to target in your chat or let the editor select the correct one based on your open files.

Yes. The MCP Server uses your configured AWS environment variables to authenticate, letting Cursor securely query your Bedrock resources without hardcoding keys.

Your AWS Bedrock vector indexes and knowledge base documents remain protected by your existing AWS IAM policies. Cursor processes the retrieved text locally inside your active workspace using this lightweight MCP setup, meaning no raw data ever persists on external intermediate servers.

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