sandboxed-browser-mcp

Overview Schema Source Related Servers Discussions Admin

Type

browser_type

Types text into a form field identified by ref, replacing its current content; set submit to press Enter and report the resulting screen changes.

Instructions

Puts text into a field by ref, replacing what it held (inputs, text areas, editable regions); submit: true presses Enter afterwards. Reports the changes on screen. Dropdowns take browser_select instead.

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": {
      "ref": "<ref>",
      "text": "<text>"
    },
    "name": "browser_type"
  }
}

Input Schema

Name	Required	Description	Default
`ref`	Yes	Ref of the field to type into (e12, f2e7 …), as browser_snapshot or browser_find showed it.
`text`	Yes	What the field should contain afterwards (its old text is replaced).
`submit`	No	true to press Enter once the text is in.
`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"
+}

Changed5 schema fields changedv1.1.0Oct 31, 2026

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

changedInput schema / properties / ref / description

Previous value: -"Element ref from the latest view or browser_find, e.g. e12 (f1e5 inside a frame)"New value: +"Ref of the field to type into (e12, f2e7 …), as browser_snapshot or browser_find showed it."

addedInput schema / properties / submit / default
```
Added value: +false
```

changedInput schema / properties / submit / description

Previous value: -"Press Enter after; default false"New value: +"true to press Enter once the text is in."

changedInput schema / properties / text / description

Previous value: -"The field's whole new text"New value: +"What the field should contain afterwards (its old text is replaced)."

First observedv1.0.0Oct 24, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutation profile is known. The description adds real value by disclosing that existing text is overwritten and that the tool "Reports the changes on screen", but it does not say what happens on failure, whether the ref can go stale, or how large the reported change set is.

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?

Three short clauses that each carry distinct information: action, Enter behavior, and return disclosure, with the sibling exclusion placed last. No redundant restatement of the title.

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?

No output schema exists, so the "Reports the changes on screen" line usefully covers the return behavior, and the field-type scope plus dropdown exclusion cover the main misuse modes for a 4-parameter mutation tool. Only failure and stale-ref behavior are left unaddressed.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description still adds meaning by clarifying that text is a replacement target rather than an append, and by restricting the ref to field-like elements (inputs, text areas, editable regions) rather than arbitrary nodes. The dropdown carve-out effectively warns that some refs will be rejected.

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?

Specific verb plus resource ("Puts text into a field by ref"), an explicit scope covering inputs, text areas and editable regions, and a named sibling it is not ("Dropdowns take browser_select instead"). An agent can distinguish this from browser_select without opening either schema.

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

Usage Guidelines4/5

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

Explicitly routes dropdowns to browser_select, which is a real when-not-to-use rule with a named alternative, and the ref parameter points at browser_snapshot/browser_find as the source of refs. No guidance on choosing between submit:true and browser_key for Enter, and no prerequisites stated, so not a full 5.

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

Deploy Server