Tinyfish MCP connector for AI agents

CALL ANY TOOL

Run browser automations, fetch JavaScript-rendered pages, and search the web with a real cloud Chrome. Same toolkit, every framework, no auth plumbing.

tinyfish_page_fetch

Fetch page

Fetch the rendered content of a URL using Tinyfish's real cloud Chrome browser, including JavaScript-heavy pages.

Parameters

Name

Type

Required

Description

url

string

Required

URL to fetch

wait_for

string

Optional

CSS selector or condition to wait for before capturing

format

string

Optional

Output format: html, text, markdown

tinyfish_automation_run

Run automation

tinyfish_search

Web search

tinyfish_screenshot

Take screenshot

tinyfish_session_create

Create session

Build your Agent

Drop the toolkit in, point it at the user, and your agent can run Tinyfish browser automations from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tinyfishmcp"], toolNames: ["tinyfish_page_fetch", "tinyfish_automation_run", "tinyfish_search"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tinyfishmcp"], toolNames: ["tinyfish_page_fetch", "tinyfish_automation_run", "tinyfish_search"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tinyfishmcp"], toolNames: ["tinyfish_page_fetch", "tinyfish_automation_run", "tinyfish_search"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/tinyfishmcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your automation agent to start running browser tasks via Tinyfish.

Fetch & extract

Copy the prompt

Copied

Fetch the content from [URL] including rendered JavaScript.

Copy the prompt

Copied

Take a full-page screenshot of [URL].

Copy the prompt

Copied

Search the web for [query] and return the top results.

Automate

Copy the prompt

Copied

Log in to [URL] and extract the data from the dashboard.

Copy the prompt

Copied

Fill out the form at [URL] with [data] and submit.

Copy the prompt

Copied

Create a persistent browser session and navigate to [URL].

SEE HOW AUTH WORKS

Users authorize Tinyfish once. Their credentials stay vaulted, every browser session runs under their account quota, and every action is logged.

1

Authorize

Your user connects

Tinyfish MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Tinyfish MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Tinyfish MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Tinyfish MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other automation and web scraping connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Tinyfish MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does Tinyfish run a real browser or headless?

Real cloud Chrome. Tinyfish renders pages exactly as a user's browser would, handling JS, cookies, and session state.

Does the agent use a shared Tinyfish account or per-user accounts?

Per-user. Each developer's Tinyfish credentials are vaulted under their identity. Browser session and quota usage is tracked per user.

Where are Tinyfish credentials stored?

In Scalekit's AES-256 vault, namespaced per tenant. They resolve at request time and never appear in prompts.

Can I restrict the agent to read-only browser operations?

Yes. Use listScopedTools to allow page_fetch and screenshot without granting automation_run or session_create.

What happens when a user's Tinyfish credentials are revoked?

The next tool call fails closed for that user. Other users remain unaffected. Revocation is logged.

Tinyfish MCP

Tools your agent reaches for on Tinyfish MCP, scoped per user.