Skip to main content
Glama
morfiade-app

io.github.morfiade-app/morfiade-mcp

Official

start_profile

Launch a Chrome profile with its own cookies, sessions, and proxy; opens a URL in a new tab if the profile is already running.

Instructions

Launch a profile: opens its real Chrome window with its own cookies, sessions and proxy. If the profile is already running, only opens the URL in a new tab of that window. Can take up to a minute and needs a valid Morfiade licence. The agent cannot drive the page afterwards through these tools; that needs browser_command, which the owner enables separately.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoAddress to open, with scheme (https://...); optional
profileYesProfile name exactly as list_profiles returns it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.1
    • changedInput schema / properties / profile / description
      Previous value: -"Profile name from list_profiles"New value: +"Profile name exactly as list_profiles returns it"
    • changedInput schema / properties / url / description
      Previous value: -"Optional URL to open"New value: +"Address to open, with scheme (https://...); optional"
  2. First observedv0.2.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already indicate mutation, open-world, and non-idempotent behavior, and the description adds substantial detail: real Chrome window, cookie/session/proxy isolation, the new-tab behavior for running profiles, a one-minute latency bound, and the licensing requirement. No important behavioral surprises are hidden.

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?

Four sentences, each carrying a distinct fact; the core action is front-loaded and the caveats (delay, license, no post-launch driving) are grouped at the end. Nothing is redundant.

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?

For a state-changing launch tool with no output schema, the description conveys the critical launch behavior, edge case, timing, prerequisites, and limitation. An agent has enough context to invoke it correctly and know what to do next.

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 the schema already documents profile and url. The description adds useful operational context (e.g., URL opens in a new tab when the profile is already running), but it only minimally elaborates on parameter-specific semantics beyond what the schema provides.

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 concrete action and resource: 'Launch a profile: opens its real Chrome window...' It clearly distinguishes the tool from siblings like list_profiles, status, and stop_profile, and explains the already-running edge case. This makes the tool's role unambiguous.

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 states when the tool is appropriate (launching a profile or opening a URL) and when it is not: the agent cannot drive the page afterwards. It names browser_command as the alternative and notes that the owner must enable it separately, plus the license prerequisite and potential delay.

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