nodriver-mcp-server

Overview Schema Source Related Servers Discussions Admin

Click element

click

Click a page element by its snapshot uid using real browser input events, so the action appears human. Scrolls the element into view, dodges overlays, and reports or bypasses blockers.

Instructions

Click an element addressed by its snapshot uid.

This is the click you want in almost all cases — prefer it over click_at, because a uid survives layout shifts and raw coordinates do not. The element is scrolled into view first, so it need not be visible beforehand.

Sends real CDP input events, so the page sees isTrusted=true, which is the entire point of an undetected driver. Because those are delivered by coordinate, the click is aimed at a point that actually hits the element: several points inside it are hit-tested first, since a sticky header or a banner can cover the centre. If none of them reach it, if_covered decides what happens, and the response always says which path was taken.

Two other situations force the scripted fallback regardless: a touch-emulated target, where CDP mouse input can crash the renderer, and a CDP click that times out or errors. Every step is bounded at 10s, so a wedged page cannot hang the call.

On "unknown uid", take a fresh take_snapshot and retry with the new uid.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`uid`	Yes	Element uid from the most recent take_snapshot, e.g. "4_12". uids are invalidated whenever the page changes — if you get "unknown uid", take a fresh snapshot and retry with the new uid.
`browser`	No	Which browser to act on. Each name is an independent Chrome, created on first use. Omit for the shared default; parallel agents each need their own name.	default
`dbl_click`	No	Send a double-click instead of a single click.
`if_covered`	No	What to do when something else sits on top of the element, so a real mouse click at its position would hit that instead. "report" (the default) does not click at all: it returns an error naming what is in the way, leaving the page untouched and the session indistinguishable from a person's. Dismiss the cookie banner, close the modal or scroll, then click again. "synthetic_click" dispatches the click on the element directly, which works through anything — but the page sees `isTrusted=false`, which is precisely the signal anti-bot systems look for. Choose it when the overlay cannot be dismissed, or when stealth does not matter on this site; not as a default.	report
`include_snapshot`	No	Append a fresh page snapshot to the response. Worth it when this action changes the page and take_snapshot would be your next call anyway — it saves a round trip, at the cost of a much larger response.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv2.5.0Sep 25, 2026

addedInput schema / properties / browser

Added value: +{
+  "default": "default",
+  "description": "Which browser to act on. Each name is an independent Chrome, created on first use. Omit for the shared default; parallel agents each need their own name.",
+  "type": "string"
+}

addedInput schema / properties / if_covered

Added value: +{
+  "default": "report",
+  "description": "What to do when something else sits on top of the element, so a real mouse click at its position would hit that instead. \"report\" (the default) does not click at all: it returns an error naming what is in the way, leaving the page untouched and the session indistinguishable from a person's. Dismiss the cookie banner, close the modal or scroll, then click again. \"synthetic_click\" dispatches the click on the element directly, which works through anything — but the page sees `isTrusted=false`, which is precisely the signal anti-bot systems look for. Choose it when the overlay cannot be dismissed, or when stealth does not matter on this site; not as a default.",
+  "enum": [
+    "report",
+    "synthetic_click"
+  ],
+  "title": "If Covered",
+  "type": "string"
+}

First observedv1.7.2Aug 7, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses far more than the annotations: real CDP input events, isTrusted=true, hit-testing behavior, fallback to synthetic clicks, touch-emulation crash risk, 10-second bounds, and response path reporting. This is exactly the behavioral context an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place: purpose, sibling differentiation, stealth behavior, fallback conditions, timeout safety, and error recovery. It is front-loaded and structured in clear paragraphs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, the rich schema, and the presence of an output schema, this description covers everything needed to invoke it correctly: when to use it, how it behaves, what can go wrong, and how to recover. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter thoroughly. The description adds some context around if_covered and uid invalidation, but it does not need to compensate for missing schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Click an element addressed by its snapshot uid.' It also explicitly distinguishes itself from click_at, so an agent can tell which tool to use without opening the sibling schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to prefer this tool over click_at and explains why, gives recovery steps for an 'unknown uid', and describes when the scripted fallback is forced. This is concrete, actionable guidance for choosing and using the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server