Use it from your agent

One ClawLink account serves every agent you run. Pick the guide for yours, or connect TinyFish once and call the same tools from all of them.

TinyFish for OpenClawInstall, pair, connect, first prompt

TinyFish for Hermes AgentInstall, pair, connect, first prompt MCPClaude Code, Cursor, any MCP clientCLI login or the remote MCP server

Setup

Connect TinyFish through ClawLink's hosted setup to let your agent browse websites, interact with pages, and complete web tasks.

Auth: Browser login (OAuth), no API keys. The credential stays on the ClawLink server; your agent holds only a ClawLink key you can revoke.
Where: the ClawLink dashboard, or ask your agent to connect it.

What your agent can do

TinyFish exposes 20 tools through ClawLink.

Tool	What it does	Kind
`tinyfish_mcp_batch_status`	Only use after batch_create to poll progress for multiple automation runs	Read
`tinyfish_mcp_discover_run`	App-only tool for discovering the currently running automation for this session	Read
`tinyfish_mcp_fetch_content`	Default, free, and most token-efficient tool for reading URL(s) and extracting source details	Read
`tinyfish_mcp_get_run`	Only use after run_web_automation errors, times out, or returns a run_id that needs polling	Read
`tinyfish_mcp_get_search_usage`	Only use when the user asks to review search history, check what queries were made, or audit	Read
`tinyfish_mcp_get_steps`	Only use when the user asks to inspect how an automation ran	Read
`tinyfish_mcp_get_wallet`	Read-only	Read
`tinyfish_mcp_guide_next_step`	Returns the next interactive TinyFish onboarding step based on the user’s real usage	Read
`tinyfish_mcp_list_browser_sessions`	Only use when the user asks to check active browser sessions, review browser usage history, or	Read
`tinyfish_mcp_list_fetch_usage`	Only use when the user asks to review fetch history or audit fetch usage	Read
`tinyfish_mcp_list_runs`	Only use when you need to find a run_id for a recently created automation, usually after	Read
`tinyfish_mcp_poll_status`	App-only tool for polling the current status of an automation run	Read
`tinyfish_mcp_search`	Default, free, and most token-efficient first tool for external knowledge and web grounding	Read
`tinyfish_mcp_batch_cancel`	Only use when the user explicitly asks to stop multiple running or pending automations	Read
`tinyfish_mcp_cancel_run`	Only use when the user explicitly asks to stop a running or pending automation	Read
`tinyfish_mcp_close_browser_session`	Only use when the user explicitly wants to stop or close a remote browser session	Read
`tinyfish_mcp_create_browser_session`	For direct browser control or visual QA, open a browser session through your wallet account	Read
`tinyfish_mcp_create_monitor`	Use when the user asks to monitor a webpage for changes or subscribe to updates about a web	Read
`tinyfish_mcp_run_web_automation`	Metered web automation is available through your wallet — use it for clicking, forms, login, or	Read
`tinyfish_mcp_run_web_automation_async`	⚠️ ONLY call this tool when the user has EXPLICITLY said they want to run the task in the	Read