How to Use the Beeceptor MCP in Vercel AI SDK

Q: How do I connect Beeceptor to Vercel AI SDK?

Install @ai-sdk/mcp and set up the HTTP transport. Pass the Beeceptor URL to createMCPClient, then feed the returned tools into your generation call.

Q: Can Vercel AI SDK stream Beeceptor mock rules to the UI?

Yes. When the agent uses createrule, the SDK yields the tool call in real-time. You render a loading state or the actual JSON configuration before the API call even finishes.

Build live API debugging dashboards in React with Vercel AI SDK handling the mock endpoints.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beeceptor MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK mock rule generation

Your React frontend needs to test edge cases without breaking production. Pass `create_rule` and `update_rule_full` to your agent. It writes the mock responses on the fly while the user watches the UI update in real-time. Clearing out old test data takes one step. Call `delete_all_rules` directly from your server action. The AI client executes the tool, letting you reset the entire proxy state before the next component render.

Stream API specs directly to the edge

Uploading OpenAPI definitions usually means clicking through a dashboard. Now you wire `upload_spec` into your Next.js chat interface. Users drop a YAML file in the browser, and the agent configures the Beeceptor endpoint instantly. State management happens right alongside the streaming response. When a test suite needs specific variables, the agent calls `upsert_state` to inject the exact payload. You check the result using `get_state_item` without leaving the Vercel edge function.

Inspect payloads with this MCP Server

Debugging webhooks requires seeing exactly what hit the URL. Expose `list_requests` to your AI SDK setup. It fetches the raw HTTP history and streams the parsed JSON straight into a Svelte or Vue data table. Sometimes a single bad payload ruins a test run. The agent isolates the problem via `get_request` and wipes it using `delete_request`. Your UI reflects the clean slate immediately.

Setup guide

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

Install `@ai-sdk/mcp` and set up the HTTP transport. Pass the Beeceptor URL to `createMCPClient`, then feed the returned tools into your generation call.

Yes. When the agent uses `create_rule`, the SDK yields the tool call in real-time. You render a loading state or the actual JSON configuration before the API call even finishes.

The HTTP transport layer supports edge environments natively. Just remember to call the client's close method when the generation completes to prevent dangling connections.

Vinkius handles the underlying auth automatically. You just need the single endpoint token provided by the marketplace, passed through the transport configuration.

Request history and mock configurations stay isolated within the Vinkius V8 sandbox. The server processes your HTTP headers and JSON bodies ephemerally, dropping the data when the session ends.

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