AI-powered browser automation and web interaction agent. Enables AI to browse, interact with websites, and perform web tasks.
AI-powered browser automation and web interaction agent. Enables AI to browse, interact with websites, and perform web tasks. On Nagent, TinyFish MCP is exposed as a fully-configurable model context protocol integration that any agent can call — 8 actions, and DCR_OAUTH authentication. No code is required to wire TinyFish MCP into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use TinyFish MCP to automate the kinds of tasks model context protocol teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire TinyFish MCP into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against TinyFish MCP, with input parameters and output schema. Drop these into any step of an agent built in Helix.
TINYFISH_MCP_CANCEL_RUNCancels a running or pending automation run by its ID. Idempotent: if the run is already in a terminal state (COMPLETED, FAILED, CANCELLED), returns the current status without error. Only PENDING and RUNNING runs will be actively cancelled.
Input parameters
Run ID
TINYFISH_MCP_DISCOVER_RUNDiscovers the currently running automation for this session. Returns runId if a run is active, or null if not yet started.
Input parameters
The session_id from the automation tool call
TINYFISH_MCP_GET_RUNRetrieves details of a specific automation run by its ID. Returns status, result, error, and other metadata. IMPORTANT: Call this after run_web_automation errors or times out — the run is likely still executing. If you do not have a run_id, use list_runs to find it. Also use this to poll for completion after run_web_automation_async. Runs typically take a few minutes. Wait 30-60 seconds between polls.
Input parameters
Run ID
TINYFISH_MCP_GET_STEPSRetrieves the steps taken during an automation run, including screenshots.
Input parameters
The run ID to get steps for
TINYFISH_MCP_LIST_RUNSLists automation runs with optional filtering by status and pagination support. Returns an array of runs with their details. Use this to find a recently created run when you do not have its run_id (e.g., after run_web_automation timed out before returning a run_id). Filter by status=RUNNING to find active runs.
Input parameters
Filter runs by goal text (case-insensitive partial match)
Maximum number of results to return (1-100)
Cursor for pagination (from previous response)
Filter by run status
Filter runs created after this ISO 8601 timestamp
Filter runs created before this ISO 8601 timestamp
Sort order by created_at
TINYFISH_MCP_POLL_STATUSPolls the current status of an automation run. Returns status, step, progress, and other metadata.
Input parameters
The run ID to poll status for
TINYFISH_MCP_RUN_WEB_AUTOMATIONExecutes web automation given a URL and a Natural Language description of the automation goal to be performed. Automation is mostly focused around navigating complex web pages and extracting data from web pages. Include _meta.progressToken in your request to receive progress notifications. WARNING: This tool may take several minutes. If it errors or times out, the run is STILL EXECUTING on the server. DO NOT call this tool again or call run_web_automation_async — both would create a duplicate run. Instead: if you have a run_id from progress notifications, call get_run. If you have no run_id, call list_runs to find it. Only create a new run after confirming the previous one finished.
Input parameters
Target website URL to automate
Natural language description of what to accomplish on the website
A unique UUID v4 identifying this request. IMPORTANT: You MUST generate a new, random UUID for every single call — never reuse a previous value or the example. Reusing a session_id will break concurrent sessions.
Proxy configuration
Feature flags to enable for this run
Name of the integration making this API call (e.g., "dify", "zapier", "n8n"). Used for analytics.
Browser profile for execution. LITE uses standard browser, STEALTH uses anti-detection browser.
TINYFISH_MCP_RUN_WEB_AUTOMATION_ASYNCStarts a NEW web automation run asynchronously and returns a run_id immediately without waiting for completion. WARNING: Do NOT use this to retry a failed run_web_automation call — that run is still executing. Use get_run or list_runs to check its status instead. Only use this tool for genuinely new tasks. Workflow: 1) Call this tool to get a run_id. 2) Wait 30-60 seconds. 3) Call get_run with the run_id to check status. 4) Repeat step 2-3 until status is COMPLETED, FAILED, or CANCELLED.
Input parameters
Target website URL to automate
Natural language description of what to accomplish on the website
A unique UUID v4 identifying this request. IMPORTANT: You MUST generate a new, random UUID for every single call — never reuse a previous value or the example. Reusing a session_id will break concurrent sessions.
Proxy configuration
Feature flags to enable for this run
Name of the integration making this API call (e.g., "dify", "zapier", "n8n"). Used for analytics.
Browser profile for execution. LITE uses standard browser, STEALTH uses anti-detection browser.
No publicly available marketplace agent is found using this tool yet. There are 73 agents privately built on Nagent that already use TinyFish MCP.
Build on Nagent
Connect TinyFish MCP to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find TinyFish MCP, and click "Connect Now." You'll authenticate with DCR_OAUTH — Nagent handles credential storage and refresh automatically. Once connected, TinyFish MCP is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once TinyFish MCP is connected, you configure its 8 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop TinyFish MCP steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a TinyFish MCP event fires, the agent kicks off automatically.
Every TinyFish MCP action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While TinyFish MCP ships with 8 pre-built model context protocol actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching TinyFish MCP together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build TinyFish MCP-based workflows tailored to your business.