TinyFish AI Web Agent MCP Server

by tinyfish-agent

answering

TinyFish AI Web Agent is answering right now. Last checked 4 min ago.

AI-powered web automation. Navigate websites using AI agents for one page or a thousand

Uptime history 61 hours of history

61 hours agonow

100.0%

Uptime 24h

92 of 92 checks

—

Tools

hidden behind auth

565 ms

Response time

average over 24h

API key or OAuth

Access

streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add web-agent --transport http https://agent.tinyfish.ai/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "web-agent": {
      "url": "https://agent.tinyfish.ai/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.web-agent]
url = "https://agent.tinyfish.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "web-agent": {
      "url": "https://agent.tinyfish.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "web-agent": {
      "url": "https://agent.tinyfish.ai/mcp"
    }
  }
}

This endpoint answered with an authorization challenge — the server is running, but you need an API key or OAuth to use it.

Endpoints

URL	Transport	State	Latency	Checked
https://agent.tinyfish.ai/mcp	streamable-http	needs key	499 ms	4 min ago

Alternatives to TinyFish AI Web Agent

same job, measured the same way

TinyFish AI Web Agent

by mino

AI-powered web automation. Navigate websites using AI agents for one page or a thousand

answering

Skyvern

by skyvern-ai

AI-powered browser automation — navigate, click, fill forms, and extract data from any website.

answering

Invoiceflow MCP

by enzoemir1

AI-powered invoice automation. Create invoices, track payments, and manage cash flow.

54 installs/wk local only

Test Genie

by muse-code-space

AI-powered app test automation for iOS, Android, Flutter, React Native, Web

72 installs/wk local only

Browserbase

by mcparmory

Create and control browser sessions for web automation, testing, and AI agent tasks

106 installs/wk local only

Kitewright

by kitewright

Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.

320 installs/wk local only

Dot AI

by vfarcic

AI-powered development platform for Kubernetes deployments and intelligent automation

91 installs/wk local only

MCP Server Browserbase

by browserbase

MCP server for AI web browser automation using Browserbase and Stagehand

3 459 installs/wk local only

TinyFish AI Web Agent — questions

Answers built from our own checks of this server.

Why is there no tool list for TinyFish AI Web Agent?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is TinyFish AI Web Agent working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 565 ms. The bar chart above shows every period we have measured.

How do I connect TinyFish AI Web Agent?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own key or an OAuth login: it refuses anonymous clients.

Does TinyFish AI Web Agent need an API key?

Yes. Every time we knock, TinyFish AI Web Agent answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is TinyFish AI Web Agent?

It answers our handshake in 565 ms on average, which is faster than 19% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.