Skip to main content
Glama

safari_native_type

Insert text as real input, in the background (Safari is never activated). Inputs and textareas get it through the macOS accessibility tree (isTrusted beforeinput/input, any language, clipboard untouched); rich editors (contenteditable) get…

Instructions

Insert text as real input, in the background (Safari is never activated). Inputs and textareas get it through the macOS accessibility tree (isTrusted beforeinput/input, any language, clipboard untouched); rich editors (contenteditable) get a real paste (Cmd+V to the Safari window). Unlike safari_fill which manipulates DOM directly (breaking React/ProseMirror state), this goes through the real paste pipeline — ProseMirror/Slate/Draft.js process the paste event natively and update their internal model. After native_type, pressing Enter (via safari_native_keyboard) will actually submit the form because the framework state matches the DOM. Saves and restores the user's clipboard. No focus stealing. Use for Discord, Slack, and any editor where safari_fill works visually but the content isn't 'really there' when you try to submit.

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": {
      "value": "<value>"
    },
    "name": "safari_native_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoRef ID from safari_snapshot to focus first
valueYesText to insert via clipboard paste
receiptNoTab receipt from safari_new_tab — pins this call to that tab (survives reconnects/subagents)
selectorNoCSS selector of the editor element to focus first

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.24.1
    • addedInput schema / properties / receipt
      Added value: +{
      +  "description": "Tab receipt from safari_new_tab — pins this call to that tab (survives reconnects/subagents)",
      +  "type": "string"
      +}
  2. Addedv2.11.6
  3. Removedv2.11.3
  4. Addedv2.10.9
  5. Removedv2.10.8
  6. Addedv2.10.5
  7. Removedv2.10.4
  8. Addedv2.7.15
  9. Removedv2.7.1
  10. Addedv2.1.7

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description carries the whole burden and delivers a lot beyond the obvious: background execution (Safari never activated), no focus stealing, clipboard saved and restored, isTrusted events, and a real Cmd+V paste pipeline. What it omits is operational friction an agent would hit in practice — macOS accessibility permissions, what happens on failure, and whether the call blocks until the paste lands. Strong disclosure but not complete for a headless-input tool.

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?

Front-loaded with the action and scope, then the mechanism, then the concrete usage cue — good ordering with no wasted opening. It runs long, and the React/ProseMirror/Slate/Draft framework name-dropping plus the repeated paste-pipeline point could be tightened without losing meaning.

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?

Complete enough for a fairly complex tool: mechanism, side effects on the live browser session, sibling differentiation, and downstream interaction with safari_native_keyboard. No output schema exists, so the definition should say what comes back (success/failure signal), and it doesn't; permissions and partial-failure behavior are also unaddressed.

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 baseline is 3, and the description adds little per-parameter meaning — it never explains how ref, selector, and receipt interact (e.g. which wins for focusing, or when receipt is needed versus optional). The clipboard-paste nature of the value parameter is already stated in the schema.

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?

States a specific verb and resource ('Insert text as real input, in the background') and immediately names the distinguishing mechanism versus safari_fill ('manipulates DOM directly … breaking React/ProseMirror state'). An agent can tell exactly what this does and how it differs from the closest sibling.

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?

Explicit when-to-use ('Use for Discord, Slack, and any editor where safari_fill works visually but the content isn't really there when you try to submit') and when-not (the DOM-manipulating safari_fill route). It also wires in the follow-on step, noting that pairing with safari_native_keyboard Enter actually submits because framework state matches the DOM.

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

Deploy Server

Other Tools