How to Use the pgvector (Vector Database) MCP in Windsurf

Q: How does Windsurf use the pgvector (Vector Database) MCP Server to run queries?

Cascade calls searchvectors using the current conversation context to find similar embeddings in your database. It handles the vector formatting and distance operators automatically, returning raw rows directly to your workspace.

Q: Can Windsurf set up HNSW indexes using pgvector (Vector Database)?

Yes. Cascade invokes createindex directly on your database, configuring the parameters for fast similarity searches. You don't need to write the raw SQL index commands yourself.

Q: How do I configure this pgvector (Vector Database) MCP Server in my Windsurf setup?

Open your mcpconfig.json file and add the server under the mcpServers key. Windsurf auto-discovers the six database tools as soon as you save the file.

Q: Does this toolset work with Windsurf's Cascade?

Absolutely. Cascade chains tools like listtables and searchvectors to inspect your database structure and run queries without waiting for your manual approval.

Let Windsurf Cascade build, index, and query embeddings inside Postgres using this pgvector (Vector Database) MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect pgvector (Vector Database) MCP to Windsurf

Create your Vinkius account to connect pgvector (Vector Database) to Windsurf — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup pgvector (Vector Database) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Database Setup in Windsurf

The `create_table` tool builds the database tables required to store your high-dimensional embeddings. Cascade detects your schema needs, runs this tool, and immediately chains `create_index` to set up HNSW or IVFFlat indexing without you prompting each step. This means you bypass the manual SQL console entirely. Your agent handles the structural setup and immediately moves to ingestion, keeping your development momentum going.

Chain Ingestion and Verification

The `insert_vector` tool writes your raw embedding arrays directly into the designated Postgres table. Cascade reads your source files, formats the vectors, calls this insertion tool, and then runs `list_tables` to check the state of your database. You don't have to write single-use python scripts to load your test data. The agent handles the file parsing and database writes in one continuous autonomous loop.

Instant Context Retrieval

The `search_vectors` tool executes cosine or Euclidean distance queries to find matching documents. Cascade uses this tool to pull relevant database context, then immediately feeds those results back into its code generation loop to fix bugs or write features. If a search returns bad matches, Cascade uses `delete_vector` to purge stale entries and runs a new query. You get accurate, self-correcting retrieval pipelines directly inside your workspace.

Setup guide

Set up pgvector (Vector Database) 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 pgvector (Vector Database) 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 pgvector (Vector Database) payment history." If connected, Cascade will call the pgvector (Vector Database) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "pgvector-vector-database-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 pgvector. 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 pgvector (Vector Database) 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 pgvector (Vector Database) MCP in Windsurf

Cascade calls `search_vectors` using the current conversation context to find similar embeddings in your database. It handles the vector formatting and distance operators automatically, returning raw rows directly to your workspace.

Yes. Cascade invokes `create_index` directly on your database, configuring the parameters for fast similarity searches. You don't need to write the raw SQL index commands yourself.

Open your `mcp_config.json` file and add the server under the `mcpServers` key. Windsurf auto-discovers the six database tools as soon as you save the file.

Absolutely. Cascade chains tools like `list_tables` and `search_vectors` to inspect your database structure and run queries without waiting for your manual approval.

Your database credentials and raw embeddings never leave your local machine or your private Vinkius sandbox. This MCP server acts as a secure local bridge, ensuring that raw SQL queries and sensitive vector dimensions remain completely isolated from external 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