devtools-fleet-mcp

Overview Schema Source Related Servers Discussions Admin

state_save

Save the current browser's login (cookies and localStorage) as a named state so other sessions can start already logged in; only cookies for allowed origins are kept.

Instructions

Save the current browser's login (cookies + localStorage) as a named state, so other sessions can start already logged in. Only cookies for the allowed origins are kept. allowedOrigins defaults to the http(s) origins open in tabs; it can never be wider than this browser's own allowlist. States a person created with devtools-fleet login cannot be overwritten.

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": {
      "name": "<name>"
    },
    "name": "state_save"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	State name: letters, digits, . _ -
`strict`	No	Block every request (not just navigations) outside the allowlist when the state is used
`overwrite`	No
`allowedOrigins`	No	Origins this state may be used on, e.g. ["https://staging.example.com"]

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 1, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and delivers meaningful behavior: allowedOrigins defaults to open http(s) tab origins, can never exceed the browser's own allowlist, and states created via `devtools-fleet login` are protected from overwrite. It doesn't spell out what cookies outside the allowlist undergo (dropped silently) or auth prerequisites, but the disclosure is strong.

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 core action, then behavioral caveats in descending importance. Four tight sentences with no filler, though the allowlist constraint is restated in two adjacent sentences.

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 stateful save operation with no annotations and no output schema, the description covers the critical behaviors an agent needs (origin scoping, overwrite protection, default derivation). Only minor gaps remain around failure modes and return behavior.

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 75% and the schema already documents name, strict, and allowedOrigins. The description adds genuine meaning beyond the schema by explaining allowedOrigins' default derivation and its hard upper bound, plus the overwrite protection behavior that bears on the overwrite flag.

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+resource+payload: 'Save the current browser's login (cookies + localStorage) as a named state.' The purpose is unambiguous and distinguishable from the sibling state_list, which the agent can infer handles the read side.

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?

The rationale 'so other sessions can start already logged in' implies when this is useful, and constraints on allowedOrigins scope are given, but there is no explicit when-to-use vs when-not guidance and no mention of the sibling state_list as an alternative.

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