How to Use the Glama MCP in Vercel AI SDK

Q: How do I connect the Glama directory to a Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the transport with your Vinkius HTTP endpoint. Pass the tools from glamalistmcpservers and glamarungatewaychat into streamText to let your agent search tools and chat.

Q: Can I stream model responses from Glama using Vercel AI SDK?

Yes. The glamarungatewaychat tool executes prompts through the Glama gateway, and you can pipe the output directly into streamText. This keeps your edge functions fast and responsive.

Q: How does Vercel AI SDK handle tool parameters from a Glama MCP Server?

The SDK reads the JSON schema exposed by glamagetmcpserverinfo to understand what arguments a specific server requires. Your agent then generates the correct arguments and executes the tool dynamically.

Q: What happens when a user searches for an offline server?

Your agent uses glamagethostedinstances to verify if a private server is actually active. If the instance is offline, the SDK can catch the error and display a fallback UI message immediately.

Q: How does Glama protect my telemetry metrics and telemetry data?

The server transmits execution metrics via glamasendtelemetry over an encrypted, ephemeral V8 sandbox connection. Only execution durations and tool names are recorded, keeping your actual prompt payloads private.

Feed live Glama model routing and directory searches directly into your React frontend using the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Glama to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic Directory Discovery via Vercel AI SDK

`glama_list_mcp_servers` queries the global database of tools based on natural language input from your application users. This tool handles loose text matching to find capabilities on the fly. When your React frontend requests a new capability, your agent runs this discovery step. The Vercel AI SDK streams the resulting server listings straight to the UI, letting users watch their workspace expand in real-time.

Unified Model Proxying at the Edge

`glama_run_gateway_chat` routes conversational prompts through the Glama proxy network using any supported model. You don't need to manage separate provider keys or install multiple SDKs in your Next.js edge functions. This MCP Server allows your client to switch models on the fly. You get a single endpoint that handles the plumbing while the Vercel AI SDK handles the streaming text chunk by chunk.

Granular Model Auditing

`glama_get_gateway_model_details` extracts the exact context window, parameter constraints, and pricing of any proxied gateway model. Your agent checks these specs before routing a large payload to avoid token limit errors. By pairing this with `glama_get_gateway_models` in your MCP Server setup, your application builds dynamic model-selector dropdowns in your UI. The Vercel AI SDK renders these options directly from live registry data without hardcoded config files.

Setup guide

Set up Glama MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Glama tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Glama transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the transport with your Vinkius HTTP endpoint. Pass the tools from `glama_list_mcp_servers` and `glama_run_gateway_chat` into `streamText` to let your agent search tools and chat.

Yes. The `glama_run_gateway_chat` tool executes prompts through the Glama gateway, and you can pipe the output directly into `streamText`. This keeps your edge functions fast and responsive.

The SDK reads the JSON schema exposed by `glama_get_mcp_server_info` to understand what arguments a specific server requires. Your agent then generates the correct arguments and executes the tool dynamically.

Your agent uses `glama_get_hosted_instances` to verify if a private server is actually active. If the instance is offline, the SDK can catch the error and display a fallback UI message immediately.

The server transmits execution metrics via `glama_send_telemetry` over an encrypted, ephemeral V8 sandbox connection. Only execution durations and tool names are recorded, keeping your actual prompt payloads private.

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