Claude Agent

Why the Claude Agent SDK + Tabstack

Wiring web access into an agent usually means hand-rolled fetches, HTML parsing, and prompt gymnastics to coax structured data out of messy text. @tabstack/claude-agent replaces that with a hosted API exposed as an in-process MCP server: schema-enforced output, server-side rendering of JS-heavy pages, and one key for extraction, research, generation, and automation. One call builds a ready-to-use server for query(), with no separate process to run.

Quickstart

Install the adapter and set your keys:

npm install @tabstack/claude-agent @anthropic-ai/claude-agent-sdk zod
 
export TABSTACK_API_KEY="your-tabstack-key"
export ANTHROPIC_API_KEY="your-anthropic-key"

@anthropic-ai/claude-agent-sdk and zod are peer dependencies. The Claude Agent SDK requires Zod 4, so this package's zod peer is ^4.0.0.

tabstackServer is a ready-built in-process MCP server, and tabstackAllowedTools pre-approves every Tabstack tool. Wire both into a query() call:

import { query } from "@anthropic-ai/claude-agent-sdk";
import { tabstackServer, tabstackAllowedTools, tabstackMcpServerName } from "@tabstack/claude-agent";
 
for await (const message of query({
  prompt: "What are Vercel's current pricing plans, with sources?",
  options: {
    mcpServers: { [tabstackMcpServerName]: tabstackServer },
    allowedTools: tabstackAllowedTools,
  },
})) {
  if (message.type === "result" && message.subtype === "success") {
    console.log(message.result);
  }
}

The server resolves TABSTACK_API_KEY lazily on first tool call, so importing the package never requires a key.

For a custom key, base URL, or a shared client, build the server explicitly:

import { createTabstackClaudeAgentServer } from "@tabstack/claude-agent";
 
const server = createTabstackClaudeAgentServer({ apiKey: process.env.MY_KEY });
// or pass an SDK client you already have: createTabstackClaudeAgentServer({ client })

Assembling the server yourself? createTabstackClaudeAgentTools(config) returns the raw tool array to pass to your own createSdkMcpServer({ name, version, tools }).

The tools

Claude sees each tool under its fully qualified MCP name, mcp__tabstack__<tool_name>. The names stay in lockstep with the @tabstack/langchain, @tabstack/ai, @tabstack/eve, and Python langchain-tabstack packages.

Good to know

• automate_browser_task runs non-interactively. It does not pause for human-in-the-loop form input, so it never blocks. It returns the final answer plus the data it extracted and the pages it visited.
• Failed calls normalize to a TabstackToolError and return as an MCP error result (isError: true), so Claude reads a useful message and can retry or explain rather than seeing a raw exception.
• Each tool's input schema is the core Zod schema's raw shape, so the Agent SDK validates the model's arguments before your handler runs.

Common use cases

• Give a Claude agent cited, multi-source research without running a browser.
• Pull structured fields off a page into a shape you define.
• Add web access to an existing query() call with two imports.
• Keep tool names consistent across your TypeScript and Python agents.

Next steps

• Adapter on GitHub
• @tabstack/claude-agent on npm
• Claude Agent SDK docs
• Get an API key