dolphin-anty-mcp

Start a temporary browser profile

start_temporary_profile

Start a temporary browser profile with a clean data directory and default fingerprint. Returns a profileId for one-off sessions that won't persist in the workspace.

Instructions

Launch a throwaway profile with a fresh data directory and default fingerprint preferences. Returns the generated profileId. Useful for one-off sessions you do not want persisted in the workspace.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_temporary_profile"
  }
}

Input Schema

Name	Required	Description
`dpr`	No	Device pixel ratio of your real display.
`headless`	No	Launch without a GUI. Implies `noTabs`.
`automation`	No	Expose the Chrome DevTools Protocol so Puppeteer/Playwright/Selenium can drive the browser. The response then carries `automation.port` and `automation.wsEndpoint`. Unavailable on the Free plan (HTTP 402).
`screenWidth`	No
`screenHeight`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 1, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only provide generic hints (readOnlyHint=false, openWorldHint=true, destructiveHint=false). The description adds useful context: it creates a fresh data directory, uses default fingerprint preferences, returns a profileId, and does not persist the session. This goes beyond the annotations without contradicting them.

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 two sentences with no filler. It front-loads the key action and outcome, then adds the usage context. Every word earns its place.

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?

The tool is moderately simple and has no output schema, but the description adequately mentions the return value (profileId) and the core behavior. It could delve deeper into lifecycle details (e.g., whether the profile is automatically deleted), but overall it is sufficient for an agent to understand the tool's purpose and basic use.

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?

The schema already includes descriptions for 3 of 5 parameters (dpr, headless, automation), covering 60%. The description itself adds no parameter-specific semantics, but the schema covers the majority. The remaining parameters (screenWidth/screenHeight) are self-explanatory from their names and constraints.

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 clearly states the action ('Launch a throwaway profile') and the resource (a temporary profile with a fresh data directory and default fingerprint preferences). It also distinguishes this from sibling tools like start_profile by emphasizing the temporary, non-persisted nature.

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?

The description explicitly says it is 'Useful for one-off sessions you do not want persisted in the workspace,' giving clear context on when to use it. However, it does not explicitly name alternatives or state when not to use it, so it falls just short of full guidelines.

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

Deploy Server