Skip to main content
Glama
oljodev

agent-eyes

by oljodev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Log in to a site without seeing the credentials

authenticate_login

Logs users into sites via a secure localhost prompt, auto-detects login fields, submits, and returns status (success, OTP, error).

Instructions

Log the user into a site with THEIR account, without the AI ever seeing the credentials. The human types username and password into a localhost secure page; the server fills them in, submits, and returns ONLY a status: success, otp_required (then call submit_2fa_code), error, push_wait, or unknown. Selectors are auto-detected when omitted, and the ones used are reported so a retry can correct them. NEVER returns a screenshot, since a 2FA or error page can render secrets — capture separately after success, then manage_session action=save. Blocks until the human answers the prompt or 180s elapse. The first sign-in to each new site asks for consent unless assumeConsent is set.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ssoNoProvider hint, e.g. "google": click "Continue with Google" and reuse the provider session already in the browser, so no password is typed for this site. Logs into the provider once if needed.
flowNoForm shape. "auto" (default) detects single-step vs identifier-first (email, then password — Google/Microsoft/Okta) and drives both. Override only to correct a misdetection.auto
sourceNo"prompt" (default) asks the human on a localhost page; "vault" pulls them from the encrypted vault for an enrolled profile (unattended). The AI never sees the values either way.prompt
profileYesShort name for the account, e.g. "github". Not a secret — it labels the secure prompt and selects a stored credential.
loginUrlNoNavigate here first. Omit to act on the open page. Not reloaded if a saved session already authenticated you there.
viewportNoSwitch to this breakpoint first. Default: keep the current one.
assumeConsentNoSkip the per-site consent prompt, for unattended runs. Default false: the first sign-in to each new site asks the human to approve it.
submitSelectorNoSelector for the submit button. Auto-detected when omitted.
passwordSelectorNoSelector for the password input. Auto-detected when omitted.
usernameSelectorNoSelector for the username/email input. Auto-detected when omitted; the result reports which one was used.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.29.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description fully carries the behavioral burden and does so thoroughly: it discloses that credentials are never visible to the AI, that selectors auto-detect and report used selectors, that screenshots are never returned, that it blocks up to 180s, and that consent is requested unless assumeConsent is set. No contradictions exist.

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 dense but well-organized, with the core purpose front-loaded. It is longer than minimal, but every sentence contributes critical operational or safety information, so the length is justified.

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 10 parameters, no output schema, and no annotations, the description provides remarkably complete guidance: return statuses, timeout behavior, security constraints, selector reporting, consent flow, and follow-up actions. An agent has enough context to call the tool correctly and interpret its result.

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?

The input schema already covers all 10 parameters at 100% coverage, so the baseline is 3. The description adds meaningful runtime context beyond the schema: auto-detection of selectors, flow auto vs override behavior, source prompt vs vault, the meaning of otp_required, and consent handling.

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?

Clearly states it logs a user into a site with their account while keeping credentials hidden from the AI. It names the specific return statuses and references related actions (submit_2fa_code, manage_session), distinguishing it from sibling tools.

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?

Explicitly says to call submit_2fa_code on otp_required, to capture a screenshot separately after success, and to use manage_session action=save. It also states when consent is skipped via assumeConsent, giving clear when/when-not 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