Skip to main content
Glama
trueoriginlabs

vibatchium

by trueoriginlabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

explore

Retrieve text from web pages that block standard requests by launching a headless browser, bypassing anti-bot challenges, and returning extracted content with optional screenshots.

Instructions

USE THIS WHEN WebFetch/WebSearch/curl GOT BLOCKED — a 403, a Cloudflare/DataDome "Just a moment..." challenge, a login/paywall, or an empty "JavaScript is required" shell: don't report failure, use this — patchright clears most such walls cold. ONE-CALL 'look at this URL', TEXT-FIRST. Does verify_url → auto-start session if needed (headless) → go → extract text. It does NOT screenshot by default: read and navigate with the returned text/selectors, and a screenshot is captured only as a FALLBACK when the page yields no usable text (canvas/image/blank SPA). This is the 80% case of 'just show me what's on this page' — use it instead of separate start/go/text calls unless you need multi-step interaction. Pass screenshot='always' to force a screenshot, 'never' to suppress even the fallback; when one is captured it comes back as a viewable image, not base64 text. Without an explicit session it runs on an OFF-BUDGET transient ephemeral session (0.7.0) — it never competes with persistent sessions for a slot and is auto-deleted afterward, so it won't touch your 'default' session.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesTarget URL — required.
leaseNoOptional lease token to present if the target session is leased (0.7.0). Threaded per-call; never read from the server's env.
intentNoOptional natural-language description (reserved for future).
sessionNoOptional session name to target (omit for the shared 'default'). On a daemon shared with other agents, pass a UNIQUE name for stateful multi-step work (go→click→fill) so you don't collide on 'default'.
full_pageNoFull-page vs viewport screenshot, when one is captured.
keep_openNoLeave session open for follow-up calls.
screenshotNoScreenshot policy. 'auto' (default): capture ONLY if the page returns no usable text (or is challenge/login walled). 'always' (or true): force a screenshot. 'never' (or false): suppress even the fallback. When captured it is returned as a viewable image block, not base64 text.auto
skip_verifyNoSkip DNS pre-check (trusted URLs only).
min_text_charsNoAuto-mode fallback threshold: capture a screenshot if the page's extracted text is shorter than this.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations are minimal (openWorldHint only), so the description carries full burden. It discloses the internal pipeline (verify_url → auto-start → go → extract text), absence of default screenshot, fallback condition, ephemeral session behavior with auto-deletion, and that screenshots return as viewable images not base64. This goes well beyond the flag hints.

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?

The description is lengthy (~200 words) and front-loaded with the critical usage trigger. Some redundancy with schema exists (e.g., screenshot policy also in parameter description), but the extra context on session behavior and fallback logic justifies the length. The structure is coherent, moving from when-to-use to workflow to parameter nuances.

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?

Given the tool's complexity (9 params, one required) and rich behavior, the description covers all essential aspects: triggers, workflow, screenshot policy, session handling, and output format (viewable image). No output schema exists, so the statement about return format is necessary and provided. Nothing critical for an agent to call it correctly is missing.

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

Parameters5/5

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

While schema coverage is 100%, the description adds substantial meaning: it explains the interplay of screenshot and min_text_chars (auto fallback threshold), clarifies ephemeral vs persistent session semantics, and notes that keeping the session open won't affect 'default'. These are not evident from schema alone.

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 precise trigger condition ('USE THIS WHEN WebFetch/WebSearch/curl GOT BLOCKED') and names the resource (URL) with a clear verb ('look at this URL'). It explicitly contrasts with sibling tools like WebFetch/WebSearch/curl and separate start/go/text calls, making the distinction unmistakable.

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 gives explicit when-to-use ('when WebFetch/WebSearch/curl got blocked') and when-not-to-use ('unless you need multi-step interaction' to use separate calls), and recommends it as the 80% case for just showing a page. It also details parameter-driven usage (screenshot='always', 'never', session naming) with practical guidance.

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