Skip to main content
Glama
Sign In
Auto-Browser

Auto-Browser

by LvcidPsyche
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

browser.fork_session

Snapshot cookies, storage state, and current URL to create an independent session for branching workflows or parallel variants; provide a start URL if the source is a navigation error page.

Instructions

Fork a session: snapshot its cookies, storage state, and current URL, then create a new independent session with that state. Useful for branching workflows or running parallel variants. Refused without start_url while the page is Chrome's error page for a stopped navigation.

Input Schema

NameRequiredDescriptionDefault
nameNoOmitted: fork-of-<source name>.
start_urlNoOmitted: the source session's current URL; refused while that is Chrome's error page for a stopped or failed navigation.
session_idNoTarget session id, from browser.create_session or browser.list_sessions. Optional when exactly one session is live; observe and act tools create one when none is.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.12.1
    • changedInput schema / properties / start_url / description
      Previous value: -"Omitted: the source session's current URL."New value: +"Omitted: the source session's current URL; refused while that is Chrome's error page for a stopped or failed navigation."
  2. Addedv1.8.1
  3. Removedv1.4.2
  4. Changed3 schema fields changedv1.0.3
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / session_id / maxLength
      Added value: +120
    • addedInput schema / properties / session_id / minLength
      Added value: +1
  5. First observedv0.5.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare a non-read-only, open-world, non-idempotent, non-destructive operation, so the description is not carrying the full behavioral burden. It adds useful context about what state is copied, that the resulting session is independent, and when forking is refused due to Chrome's error page.

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 sentences, front-loaded with the core action, followed by usage context and then a specific failure condition. Every sentence contributes useful information, and there is no redundant or vague phrasing.

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?

Given three optional parameters, full schema descriptions, and no output schema, the description covers the essential behavior and refusal condition completely enough to call the tool correctly. It could optionally mention the return value or default naming, but those are handled by the schema.

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 description coverage is 100%, so all three parameters are already documented in the input schema. The description only reinforces the start_url refusal condition and does not add semantics for name or session_id beyond what the schema provides, so the baseline of 3 is appropriate.

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 ('Fork a session') and immediately specifies what is snapshotted: cookies, storage state, and current URL. The phrase 'new independent session with that state' distinguishes it from browser.create_session, so an agent can choose correctly without reading the 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?

Gives clear usage contexts ('branching workflows or running parallel variants'), which is enough to know when the tool is appropriate. It does not explicitly name alternatives such as browser.create_session for a clean session, or state when not to fork.

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