How to Use the Greptile MCP in Vercel AI SDK

Q: What happens if a repository index is stale in my Greptile and Vercel AI SDK app?

Your application can trigger the reindexrepository tool to force an update of the codebase. You can trigger this automatically whenever a user pushes a new commit to their main branch. The SDK handles the asynchronous update while your UI displays the pending status.

Q: How do I monitor my Greptile API usage inside a Vercel AI SDK project?

You call getgreptileusage to pull your current token consumption and remaining credit balance. This lets you build defensive guardrails directly into your middleware to throttle heavy users before you hit hard limits.

Stream real-time codebase answers directly into your Next.js or React UI with Greptile and 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 Greptile MCP to Vercel AI SDK

Create your Vinkius account to connect Greptile 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 Greptile with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Codebase Answers to the UI

The `query_codebase` tool feeds raw repository insights directly into your streaming UI components. You don't make your users stare at a static loading spinner while the model processes complex repository architecture. Instead, the model spits out answers chunk by chunk as it scans your files. This setup works directly on the edge. You initialize the Vercel AI SDK client, hook up the MCP Server, and pipe the token stream straight to your front-end components. It keeps your serverless execution times low and your interface snappy.

Real-time Repository Status Tracking

The `get_repository_status` tool lets your application track the progress of ongoing code indexing jobs. You can build a live progress bar in your React app that updates every few seconds. It stops users from guessing whether their massive repo is ready for querying. Combining this with `list_repositories` gives your users a clean dashboard of their active codebases. You write a simple polling loop in Next.js that shuts off the moment the status returns complete.

Direct Code Search via Vercel AI SDK

The `search_codebase` tool locates exact code snippets across your entire repository using natural language. Your users can find specific helper functions or component declarations without manually browsing GitHub. The tool returns precise file paths and line numbers instantly. Developers get immediate context by pairing this with `search_by_filepath` to pull the exact lines they need. You wire these tools into your MCP application's chat interface to let users inspect code files side-by-side with the chat window.

Setup guide

Set up Greptile 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 Greptile 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 Greptile 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 Greptile. 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 Greptile 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 Greptile MCP in Vercel AI SDK

You pass your authorization token through the authProvider configuration when setting up the HTTP transport. This keeps your API keys secure on the server side while your Next.js Edge Functions handle the requests. Your AI client automatically injects the credentials into every MCP tool call.

Yes, the Vercel AI SDK allows you to stream tokenized responses directly from the query_codebase tool to your frontend. You use streamText and pass the MCP tools directly into the function call. This avoids blocking UI updates and keeps the user experience highly responsive.

Your application can trigger the reindex_repository tool to force an update of the codebase. You can trigger this automatically whenever a user pushes a new commit to their main branch. The SDK handles the asynchronous update while your UI displays the pending status.

You call get_greptile_usage to pull your current token consumption and remaining credit balance. This lets you build defensive guardrails directly into your middleware to throttle heavy users before you hit hard limits.

The server transmits your raw codebase files and repository metadata through an encrypted transit tunnel to generate the vector index. Once indexed, your code remains stored in a sandboxed, zero-trust environment that never shares data with external training sets. You can delete this data at any point using the delete_repository tool.

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