How to Use the Glama MCP in Windsurf

Q: How does Windsurf handle Glama gateway model switching?

Cascade reads the available models using glamagetgatewaymodels first. It then uses glamarungatewaychat to execute prompts against different models depending on the task complexity.

Q: How does Glama protect my private model prompts and telemetry data in Windsurf?

Telemetry metrics sent via glamasendtelemetry and chat prompts from glamarungatewaychat run through Vinkius's ephemeral V8 sandboxes. Your data is processed in transit and never stored on persistent disks.

Let Windsurf Cascade search the Glama directory and auto-route model requests on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glama MCP to Windsurf

Create your Vinkius account to connect Glama 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 Glama with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic tool discovery for Windsurf Cascade

Cascade can now search the global repository of servers without you leaving your workspace. When you ask for a tool you don't have, Cascade uses `glama_list_mcp_servers` to find it and pulls setup steps via `glama_get_mcp_server_info`. This cuts out manual web searches. By inspecting `glama_get_mcp_attributes`, Cascade understands what capabilities are out there and plans its next execution chain based on live registry data.

Run multi-model chains inside Windsurf

Stop hardcoding model endpoints in your Windsurf configuration. This MCP integration lets Cascade use `glama_get_gateway_models` to check which models are online and routes complex reasoning steps through `glama_run_gateway_chat`. If a specific task needs a heavy reasoning model, Cascade grabs the specs with `glama_get_gateway_model_details` and fires the prompt. You get multi-model flexibility inside a single Windsurf session.

Track Windsurf execution metrics via Glama

Cascade can list your team's private servers using `glama_get_hosted_instances` to keep your proprietary tools close at hand. This MCP setup keeps your workspace clean by loading only what your immediate task requires. After running a sequence, Cascade sends execution logs back with `glama_send_telemetry`. Your team gets complete visibility into which tools are actually helping Windsurf solve problems.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "glama-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 Glama. 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 Glama 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 Glama MCP in Windsurf

Open your Settings, head to Cascade, and find the MCP Servers UI to add it. You can also paste the Vinkius URL directly into your `~/.codeium/windsurf/mcp_config.json` file under the mcpServers key.

Yes, Cascade excels at this. When you set a goal that requires external data, Cascade automatically calls `glama_list_mcp_servers` to find the right server and then reads its setup details.

Cascade reads the available models using `glama_get_gateway_models` first. It then uses `glama_run_gateway_chat` to execute prompts against different models depending on the task complexity.

No, Vinkius handles the underlying authentication. Windsurf connects using a single endpoint token, which gives Cascade full access to all eight directory and gateway tools under this MCP Server.

Telemetry metrics sent via `glama_send_telemetry` and chat prompts from `glama_run_gateway_chat` run through Vinkius's ephemeral V8 sandboxes. Your data is processed in transit and never stored on persistent disks.

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