How to Use the Celoxis MCP in Vercel AI SDK

Connect Vercel AI SDK to Celoxis and stream live project timelines directly into your Next.js frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Celoxis MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Celoxis Portfolios via Vercel AI SDK

Calling `list_portfolios` and `list_projects` feeds top-level aggregate data straight into your agent. Vercel AI SDK takes that raw JSON and streams it to your React components as it generates. You get physical IDs, status markers, and timeline data rendering instantly on the page. Digging deeper requires `get_project` to fetch the complete intrinsic structure of a specific ID. Edge functions handle the fetch while your UI updates frame by frame. End users watch the WBS build itself live instead of staring at a blank screen.

Render Expenses and Timesheets Live

The `list_expenses` and `list_time_entries` tools pull billable and non-billable accounting records mapped to specific task items. Passing these to `streamText` lets your application display actual logged hours as the AI parses the ecosystem. Accounting dashboards suddenly feel responsive. Managers waiting on `list_approvals` see pending and cleared constraints appear instantly. Custom frontends consume the MCP Server output piece by piece. Financial bottlenecks become obvious when the data flows directly into your Svelte or Vue views.

Build Real-Time WBS Dashboards

Executing `list_tasks` combined with `list_milestones` maps absolute phase delivery tracking inside your active projects. Developers use this to populate complex Gantt charts or Kanban boards on the fly. Concrete deliverables stream straight from the source into the DOM. Tracking custom blockages happens through the `list_issues` tool. Whenever an end user asks about a delayed phase, the AI queries the matrix and pipes the blocked items back. This response hits the browser exactly when the LLM decides what to say.

Setup guide

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

Install the required packages via npm. Create your MCP client using the HTTP transport and pass your Vinkius endpoint URL. Trigger the tools method and feed the result into your generation function.

Yes, the integration handles streaming natively. Interfaces receive timesheet records in chunks as the agent processes them. Users see the accounting data populate immediately.

Running this setup on the edge works perfectly. HTTP transport layers connect to Vinkius without requiring heavy Node.js dependencies. Fast response times keep your frontend snappy.

Parallel execution depends on your specific LLM provider. Most modern models will request project details and milestones simultaneously. MCP SDKs manage those concurrent requests and stream the combined output back to you.

Vinkius isolates your billable expenses and timesheet records inside a V8 sandbox. Each session is completely ephemeral and dies after the request finishes. Zero keys ever leave the secure environment.

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