KitchenSink4Web

Official

by KitchenSink4AI

Overview Schema Source Related Servers Discussions Admin

Python

Local

Manage Session

manage_session

Destructive

Manage browser sessions for web automation: open or close browsers, inspect status and token budgets, and configure auth, device, viewport, locale, and timezone.

Instructions

One session is one browser. open starts one on a chosen lane (the first navigate of a conversation can open one for you, and says so when it does); close ends the browser; with auth state saved, the login survives; the session never does. status reads liveness first, so a dead browser says so, then lists every session this server holds with its pages, budgets, and what is shared: sessions belong to the server process, not to a conversation. capabilities, budget, and reset_budgets report and manage limits. handoff hands the window to the human for a login, an MFA prompt, or a bot wall. export_handle and import_handle move a live session between conversations on this machine: see get_workflows(task='session-transfer'). lanes is the local lane database (status, export, import, erase). profiles reloads site profiles from disk. On open, auth_state loads a saved login, contexts=2 gives one session two independent cookie jars, and device, viewport, locale, and timezone set what pages in this session believe about their environment.

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": "manage_session"
  }
}

Input Schema

Name	Required	Default
`op`	No
`lane`	No
`note`	No
`path`	No
`site`	No
`token`	No
`action`	No	status
`device`	No
`locale`	No
`reason`	No
`context`	No
`session`	No
`contexts`	No
`timezone`	No
`viewport`	No
`auth_state`	No
`expires_minutes`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 9, 2026

TDQS

B3.3/5.0

Behavior4/5

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

Annotations (destructiveHint=true, readOnlyHint=false) already flag mutation, and the description adds substantial value on top: close kills the session but saved auth survives, status reads liveness first so dead browsers are reported, and sessions belong to the server process, not the conversation. This ownership and persistence disclosure is exactly the kind of behavior an agent needs and that structured fields cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence is information-dense with no filler, and the core concept is front-loaded in the opening clause. However, the structure is a single unbroken prose paragraph mixing operation semantics, parameter effects, and cross-references; a dispatcher of this complexity would be far more scannable as bullets or an op-to-semantics table.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 17 parameters, 11 sub-operations, no output schema, and no enums, the description provides substantial orientation: it discloses status output shape, session lifetime, liveness checking, and shared-state semantics. Yet it leaves major gaps — the op/action dispatch relationship, output of most operations, and the meaning of expires_minutes, note, reason, path, site, and token — so it is only partially complete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for 17 parameters, but it only explains a subset: auth_state, contexts, device, viewport, locale, timezone, and lane. Critical dispatcher parameters — op, action, session, note, reason, path, site, token, context, expires_minutes — are never mapped to their effects, leaving an agent to guess at the mechanics of calling this tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description anchors on a strong core metaphor ('One session is one browser') and enumerates every sub-operation (open, close, status, handoff, lanes, profiles, etc.), which clearly distinguishes it from siblings like get_page_view, navigate, and monitor. However, 'manage session' is a generic dispatcher verb, and the purpose must be excavated from a dense wall of text rather than stated as a crisp mission.

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?

There is real usage context: it tells the agent that the first navigate may auto-open a session, that handoff is for login/MFA/bot walls, and explicitly points to get_workflows(task='session-transfer') for session transfer. But it never states when NOT to use this tool versus siblings such as monitor or manage_tabs, and per-operation selection guidance is minimal for a dispatcher with 11 operations.

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

Deploy Server