sandboxed-browser-mcp

Overview Schema Source Related Servers Discussions Admin

Find

browser_find

Read-only

Searches the whole page, on screen or not, for elements whose name or text holds every given word, listing up to 15 closest to view with refs and distance ready to act.

Instructions

Looks through the whole page, on screen or not, for elements whose name or text holds every given word. Lists up to 15, closest to the view first, each with its ref and its distance from the view, ready to act on.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "browser_find"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	The words to look for; an element matches when its name or text has all of them (any case).
`profile`	No	Which browser profile (a separate signed-in session) to use. Leave it out for the default one; name another only when the user's task names it. Profiles: default.	default

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.2.0Nov 12, 2026

addedInput schema / properties / profile

Added value: +{
+  "default": "default",
+  "description": "Which browser profile (a separate signed-in session) to use. Leave it out for the default one; name another only when the user's task names it. Profiles: default.",
+  "type": "string"
+}

Changed2 schema fields changedv1.1.0Oct 31, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / query / description

Previous value: -"Words to match, e.g. add to cart"New value: +"The words to look for; an element matches when its name or text has all of them (any case)."

First observedv1.0.0Oct 24, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare read-only and open-world behavior, but the description adds substantial context beyond them: it searches off-screen content, caps results at 15, orders by proximity to the viewport, and returns both a ref and a distance. It does not state what happens on a zero-match result or whether results go stale after page changes, which keeps it short of a 5.

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

Conciseness4/5

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

Two dense sentences that front-load the search scope and then the result shape, with no filler. The closing phrase 'ready to act on' is the only mildly vague wording, but it usefully signals the refs are reusable.

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

Completeness4/5

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

For a two-parameter read tool with no output schema, the description covers what is searched, the result cap, ordering, and the per-result fields, which is close to complete. It omits empty-result behavior and any note that a re-query may be needed after page mutation, leaving minor gaps.

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 coverage is 100%, so both query and profile are already documented, including the all-words-must-match rule and the profile guidance. The description restates the AND semantics of query without adding format, tokenization, or matching details beyond the schema, so the baseline of 3 applies.

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

Purpose4/5

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

States a specific verb and resource: searches the whole page (including off-screen content) for elements whose name or text contains all given words, and returns up to 15 with refs. It is clearly distinct from browser_screenshot or browser_get_text by its emphasis on matching elements and returning refs, though it never names a sibling to differentiate from explicitly.

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

Usage Guidelines3/5

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

Usage is only implied: 'ready to act on' hints the returned refs feed interactive tools like browser_click or browser_type, and the whole-page scope hints at use when the element is not yet visible. There is no explicit when-to-use, when-not-to-use, or named alternative such as browser_snapshot or browser_get_text.

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

Deploy Server