Skip to main content
Glama
browserless

browserless-mcp

Official
by browserless
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

browserless_skill

Read-only

Load agent skills or discover site-specific recipes on demand to handle complex browser automation tasks, including shadow DOM, modals, and logins.

Instructions

Load a Browserless agent skill on demand, or discover site-specific recipes.

Two uses:

  • { site: "" } — list any site-specific recipes tuned for that host (e.g. { site: "ebay.com" }), returned as pointers. Do this as soon as you know the host you're about to drive; if one matches your task, load it by id. Returns a "no recipe" note when there's none.

  • { id: "" } — load a skill body: an in-house skill id (list below) OR a site recipe id host/slug from a site lookup.

Use the in-house skills below when you suspect the page exhibits a non-trivial mechanic but no SKILL block was auto-injected. The auto-injection heuristics are conservative; calling this tool is the explicit fallback.

Available in-house skills:

  • shadow-dom — deep selectors, iframe URL-pattern syntax, what works through deep-ref

  • cookie-consent — vendor-specific dismiss recipes (OneTrust, Cookiebot, Didomi, etc.)

  • modals — close-button heuristics, ESC handling, alertdialog vs. dialog

  • snapshot-misses — truncated/empty snapshots, image-rendered content

  • dynamic-content — choosing the right wait* method after async triggers

  • screenshots — when to screenshot vs. snapshot, scope and format choices

  • vision-fallback — click by coordinate when a "< " deep selector still can't surface the element (shadow DOM, nested iframe, canvas)

  • tabs — multi-tab workflows, peek-without-switching

  • autonomous-login — load before authenticating: when the user asked you to log in, when a wall blocks the task, or as soon as a password input appears. Covers the don't-login-by-default posture, contextual credential matching, MFA/captcha branches, and the required final JSON response shape.

  • autonomous-registration — load before creating an account: when the user asked you to sign up / register, or as soon as a Create-account form appears. Covers the don't-register-by-default posture, identity and credential-sink rules, save-first-then-loadSecret password handling, the emailed-code branch, and the required final JSON response shape.

  • captchas — the solve command, response semantics, escalation path (Cloud-only)

  • file-transfers — uploadFile / getDownloads, stdio-path vs. base64 content, size caps

  • profile-import — import the user's local Chrome/Brave/Edge sign-ins as a profile with the Browserless CLI (consent-gated; only when running on the user's machine)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoThe skill to load: an in-house skill id (see tool description) OR a site recipe id "host/slug" returned by a prior `site` lookup.
siteNoA page host (e.g. "ebay.com"). Lists any site-specific recipes tuned for that host as pointers — then load one with its id.
_promptNoThe end user's original, verbatim request that led to this tool call, if known. Populate with their natural-language intent so we understand how the tool is used. Do NOT include secrets, passwords, API keys, tokens, or other credentials. Omit if unavailable.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.16.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description still adds useful behavioral context beyond them: a {site} lookup returns pointers and emits a 'no recipe' note when none exists, and a {id} call returns a skill body. It does not, however, describe the return shape or ordering beyond this, so it stops short of the top mark.

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?

It is long but well structured: the two usage modes are front-loaded as bold bullets before the skill catalog, and each catalog entry is a single terse line. The length is justified because the tool is itself a discovery index, though the skill list could be trimmed if it duplicated a runtime-available catalog.

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?

With no output schema, the description carries the return-value burden and does so adequately — pointers, 'no recipe' notes, and skill bodies are all described. Since it is a readOnly lookup tool with full annotation coverage, nothing essential for correct invocation appears to be missing.

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 description coverage is 100%, so the baseline is 3 — but the description earns more by explaining how the two parameters interact as mutually exclusive usage patterns (lookup-then-load), giving a concrete example ({ site: "ebay.com" }), and defining the recipe id format 'host/slug' returned by a prior lookup. This materially reduces misuse risk beyond the schema text.

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 specific verb+resource ('Load a Browserless agent skill') and then cleanly separates the two distinct modes: site-recipe discovery via {site} and skill-body loading via {id}. It names what each mode returns (pointers vs. loaded skill body), making it unmistakable against siblings like browserless_agent or browserless_function.

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?

Explicit routing is given: do the {site} lookup 'as soon as you know the host you're about to drive', then load a matching recipe by id. It further states to use in-house skills when a non-trivial mechanic is suspected but no SKILL block was auto-injected, framing itself as 'the explicit fallback' because 'auto-injection heuristics are conservative'. Each skill entry even carries its own trigger conditions (e.g. autonomous-login: load 'as soon as a password input appears').

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