How to Use the Amazon Bedrock KB MCP in Windsurf

Feed your AWS Bedrock vector stores directly to Cascade inside Windsurf for autonomous RAG workflows.

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 Windsurf

Create your Vinkius account to connect Amazon Bedrock KB to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run autonomous vector searches inside Windsurf

The `retrieve` tool lets Cascade search your AWS vector index without manual prompting. You ask a high-level question, and Cascade queries the index, pulls the raw chunks, and writes the code based on the actual retrieved data. This MCP Server handles the connection to AWS Bedrock behind the scenes. You don't have to copy-paste search results or write Python scripts to query your vector store.

Ground Cascade in live Bedrock Knowledge Bases

The `retrieve_and_generate` tool gives Cascade the ability to synthesize answers using your private AWS knowledge source. Cascade reads the grounded response, analyzes the context, and writes the exact files you need. Instead of guessing APIs, your agent pulls verified facts from your AWS Bedrock KB. It stops hallucinating library versions because it works only with your uploaded specs.

Track data syncs without leaving Windsurf

The `list_ingestion_jobs` tool lets Cascade check if your vector database is up to date before running queries. If a sync is pending, Cascade waits or alerts you, keeping your workspace in sync with your cloud infrastructure via the MCP Server. You can also use `list_data_sources` and `get_knowledge_base` to inspect your setup. Cascade handles the multi-step inspection autonomously, mapping out your cloud data sources in seconds.

Setup guide

Set up Amazon Bedrock KB MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Amazon Bedrock KB 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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Amazon Bedrock KB payment history." If connected, Cascade will call the Amazon Bedrock KB tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade uses the retrieve tool to query your AWS vector indexes. It injects the context directly into its planning loop to write code based on your actual data.

No, but it uses the ingestion tracking tool to verify sync status. This lets Cascade know if it is working with fresh or stale vector data before drafting files.

No, Vinkius manages the authentication securely in a sandboxed environment. You only need to paste your single Vinkius connection token into your Windsurf configuration.

The server exposes a tool to list active databases so your agent can see every available vector store. Cascade selects the correct ID and queries it based on your prompt.

Your vector embeddings and KB documents remain inside AWS Bedrock. Only the specific text chunks retrieved by the MCP are sent to Windsurf to help Cascade complete your tasks.

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