> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to Tabstack

The Tabstack connector lets your AI agent act in each user's Tabstack account. Each user connects their own Tabstack access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 4 tools.

**Authentication:** Bearer Token
**Categories:** Search, AI
**Tools:** 4: 4 read, 0 write, 0 destructive
**Users sign in with:** Access token
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=TABSTACK)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Tabstack connection

   In **AgentKit > Connections**, create a Tabstack connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'tabstack'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Tabstack:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'tabstack_extract_markdown',
     toolInput: { url: 'https://example.com/pricing' },
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "tabstack"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Tabstack:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={"url":"https://example.com/pricing"},
       tool_name="tabstack_extract_markdown",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Tabstack credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'tabstack_extract_json',
  toolInput: {
    json_schema: {},
    url: '<url>',
  },
  connector: 'tabstack',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="tabstack_extract_json",
    tool_input={
        "json_schema": {},
        "url": "<url>",
    },
    connection_name="tabstack",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `tabstack_extract_json`

Extract Page Data as JSON · Read-only

Fetch a web page and extract the data on it into JSON that matches a schema you give.
Returns a JSON object shaped by the schema.
Use tabstack_extract_json for data already on the page. Use tabstack_generate_json to summarise or derive data that is not on the page.

Read only: yes. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `json_schema` (`object`, required): JSON Schema of the data to extract. Give each property a description; properties named page_title or favicon are filled from page metadata when the page has no value. Example: {"type": "object", "properties": {"plans": {"type": "array", "items": {"type": "object", "properties": {"name": {"type": "string"}, "price": {"type": "number"}}}}}}.
- `url` (`string`, required): URL of the page to extract from. Example: https://example.com/pricing.
- `effort` (`string`, optional): Fetch effort: min is fastest with no fallback (1-5 s), standard is balanced (default, 3-15 s), max renders the page in a full browser for JavaScript-heavy sites (15-60 s). Example: standard. One of: `min`, `standard`, `max`.
- `geo_country` (`string`, optional): Fetch the page from this country, as an ISO 3166-1 alpha-2 code. Example: US.
- `nocache` (`boolean`, optional): true to bypass Tabstack's cache and fetch fresh content. Example: false.

Example input: `{"json_schema":{},"url":"<url>"}`

### `tabstack_extract_markdown`

Extract Page as Markdown · Read-only

Fetch a web page and convert it to clean Markdown.
Returns the page content as Markdown, plus Open Graph and HTML metadata when requested.
Use tabstack_extract_markdown to read a page. Use tabstack_extract_json to pull specific fields into a schema.

Read only: yes. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `url` (`string`, required): URL of the page to convert. Example: https://example.com/pricing.
- `content` (`string`, optional): main returns the main article content (default); full returns the whole page, including navigation, footer and links. Example: main. One of: `main`, `full`.
- `effort` (`string`, optional): Fetch effort: min is fastest with no fallback (1-5 s), standard is balanced (default, 3-15 s), max renders the page in a full browser for JavaScript-heavy sites (15-60 s). Example: standard. One of: `min`, `standard`, `max`.
- `geo_country` (`string`, optional): Fetch the page from this country, as an ISO 3166-1 alpha-2 code. Example: US.
- `metadata` (`boolean`, optional): true to also return the page's Open Graph and HTML metadata. Example: false.
- `nocache` (`boolean`, optional): true to bypass Tabstack's cache and fetch fresh content. Example: false.

Example input: `{"url":"<url>"}`

### `tabstack_generate_json`

Generate JSON from a Page · Read-only

Fetch a web page and have a model transform its content into JSON that matches a schema, following your instructions.
Returns a JSON object shaped by the schema.
Use tabstack_generate_json to summarise, classify or restructure a page. Use tabstack_extract_json to copy data that is already on the page.

Read only: yes. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `instructions` (`string`, required): How to transform the page content, up to 20,000 characters. Example: Summarise each plan and who it suits.
- `json_schema` (`object`, required): JSON Schema of the output to produce. Example: {"type": "object", "properties": {"plans": {"type": "array", "items": {"type": "object", "properties": {"name": {"type": "string"}, "price": {"type": "number"}}}}}}.
- `url` (`string`, required): URL of the page to read. Example: https://example.com/pricing.
- `effort` (`string`, optional): Fetch effort: min is fastest with no fallback (1-5 s), standard is balanced (default, 3-15 s), max renders the page in a full browser for JavaScript-heavy sites (15-60 s). Example: standard. One of: `min`, `standard`, `max`.
- `geo_country` (`string`, optional): Fetch the page from this country, as an ISO 3166-1 alpha-2 code. Example: US.
- `nocache` (`boolean`, optional): true to bypass Tabstack's cache and fetch fresh content. Example: false.

Example input: `{"instructions":"<instructions>","json_schema":{},"url":"<url>"}`

### `tabstack_research`

Research the Web · Read-only

Answer a question with a cited synthesis of several live web sources.
Returns Tabstack's server-sent event stream as text; the final complete event carries the report and its sources.
Use tabstack_research for an open question. Use tabstack_extract_markdown or tabstack_extract_json when you already know the URL.

Read only: yes. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `query` (`string`, required): The question to research, up to 10,000 characters. Example: Compare pricing and free tiers of the top 3 product analytics tools.
- `fetch_timeout` (`integer`, optional): Seconds to wait for each source page. Example: 10.
- `mode` (`string`, optional): fast for a quick answer (default) or balanced for standard, deeper research. Example: fast. One of: `fast`, `balanced`.
- `nocache` (`boolean`, optional): true to bypass Tabstack's cache and fetch fresh content. Example: false.

Example input: `{"query":"<query>"}`

## Related

Other Search connectors ([all 89](/agentkit/connectors/?category=search)):

- [Supadata](/agentkit/connectors/supadata/): Scalekit connector, API key, 21 tools
- [Exa](/agentkit/connectors/exa/): Scalekit connector, API key, 21 tools
- [Brave Search](/agentkit/connectors/brave/): Scalekit connector, API key, 18 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
