Skip to main content
Glama

autologin-mcp is an open-source Model Context Protocol (MCP) server that lets AI coding agents such as Claude Code log in to the web app they are testing. When the agent's browser tab shows a login form, a "session expired" message, a 401/403 or a redirect to a login page, the agent calls the login tool, and autologin-mcp fills the form with credentials stored on your machine. The username and password never appear in the conversation, so they never reach the model. It works with Claude in Chrome, Playwright MCP and chrome-devtools-mcp, and needs no browser setup.

You:            "Test the checkout flow on staging"
Agent:          …navigates… the session has expired, the app shows a login form
Agent:          calls autologin.login({ url })                 ← no password in the request
autologin-mcp:  returns a one-time script                      ← no password in the response
Agent:          runs it in the tab → { "status": "success" }   ← the page got the password from your machine
Agent:          continues the checkout test

Quick use

Requirements: Node.js 22.12+, Claude Code, and a browser tool for the agent (for example Claude in Chrome).

# 1. Register the MCP server, skill and guard hook in Claude Code
npx autologin-mcp install

# 2. Add a login profile. Run this in a normal terminal, not in the AI chat.
npx autologin-mcp add
#   Profile name (e.g. staging): staging
#   Root URL (e.g. example.com or localhost:3000): staging.example.com
#   Username: qa@example.com
#   Password (hidden):
  1. Restart Claude Code and test as usual. When the app asks for a login, the agent calls login by itself.

  2. Optional: turn on chrome://inspect/#remote-debugging in Chrome (144+) to let autologin-mcp fill the tab directly (CDP mode).

Upgrade with npx autologin-mcp@latest install, remove with npx autologin-mcp uninstall. Step-by-step guide: Getting started.

Related MCP server: byob

Why

  • Sessions expire in the middle of long agent runs. The agent stops, or asks you for the password.

  • A password pasted into the chat becomes part of the conversation. It is sent to the model provider and ends up in transcripts, logs and context summaries.

  • A password in a file the agent can read (a project .env, a prompt file) has the same problem, and can end up in git.

autologin-mcp splits the work: the agent decides when to log in; a small deterministic program on your machine does the how, with no AI involved. It finds the login form, fills it, submits it and reports only the outcome.

Documentation

The full documentation is in docs/ and on the website. The essentials:

How it works

  • Bridge mode (default, zero setup). login returns a one-time loader script containing only a 60-second URL on 127.0.0.1. The agent runs it in the tab with the JavaScript tool it already has (javascript_tool, browser_evaluate or evaluate_script). The page then fetches the credentials from your machine, and they are released only if the page's browser-set Origin header belongs to the profile's site.

  • CDP mode (automatic when Chrome remote debugging is on). autologin-mcp connects to Chrome over the DevTools Protocol and fills the tab itself; the agent runs nothing.

  • The filler works with React, Vue and Angular forms, waits for the outcome, and returns success, submitted, or failed with the page's error message.

More: How it works.

The credentials file

npx autologin-mcp add writes ~/.autologin-mcp/credentials.env (permissions 600). It is global, outside your projects, so it never ends up in git. Edit it with npx autologin-mcp edit:

STAGING_URL=staging.example.com
STAGING_USERNAME=qa@example.com
STAGING_PASSWORD='p@ss w0rd#1'      # quote values that contain spaces or #

LOCAL_URL=localhost:3000
LOCAL_USERNAME=admin
LOCAL_PASSWORD=admin
LOCAL_SUBMIT_SELECTOR=button[type=submit]   # optional, for unusual forms

A profile only fills pages whose host matches its root URL (example.com, *.example.com, localhost:3000). Several accounts for the same app are fine. More: Configuration.

MCP tools

Tool

What the agent gets back

list_profiles

Profile name, root URL and username for each profile. Never passwords.

login({ url?, profile? })

Bridge mode: run_in_page with a one-time script/function to run in the tab. CDP mode: the result directly (success, submitted, failed, no_login_form, rate_limited, …).

login_status({ profile? })

The latest outcome per profile, for when the agent's JavaScript call was cut off.

open_config

Opens the credentials file in your editor. The content is never returned.

More: MCP tools and CLI reference.

Security in one paragraph

A Claude Code guard hook and deny rules block the agent from reading the credentials folder, also in skip-permissions mode. Every tool result is scrubbed of passwords. The bridge listens on 127.0.0.1 only, each script works once for 60 seconds, and credentials go only to the profile's origin, so a prompt-injected page on another site gets nothing. Three failed logins in five minutes pause a profile, so a wrong password cannot lock the account. autologin-mcp prevents accidental exposure, not a deliberately hostile agent: use dedicated test accounts. More: Security model.

Works with

Agent / browser tool

Status

Claude Code + Claude in Chrome

Supported and tested end to end

Claude Code + Playwright MCP

Supported (browser_evaluate, or CDP with a shared browser)

Claude Code + chrome-devtools-mcp

Supported (evaluate_script, or CDP with a shared browser)

Other MCP clients

The stdio server runs; installer, skill and guard hook are Claude Code only

More: Agents and browser tools and Troubleshooting.

FAQ

How do I let Claude Code log in to my web app without giving it my password? Install autologin-mcp, add a profile for your app in a normal terminal, and restart Claude Code. When the app shows a login form, Claude calls login and autologin-mcp fills the form with the credentials on your machine. Claude only sees the outcome.

Does the password ever reach the AI model? No. It goes from the local credentials file straight into the page, through the origin-checked 127.0.0.1 bridge or the Chrome DevTools Protocol. Tool results are redacted, and a guard hook blocks reads of the credentials file.

Do I need Chrome remote debugging? No. Bridge mode needs no browser setup. Remote debugging enables CDP mode, which also works when the app's Content-Security-Policy blocks the bridge.

Does it support SSO, 2FA or multi-step logins? Not yet: it handles username + password forms on the app's own page. Multi-step logins, iframes, SSO hosts and TOTP are on the roadmap.

Is it free? Yes, MIT licensed.

More questions: FAQ.

Roadmap

  • Opt-in auto-login (CDP mode): watch a profile's URL and log in without the agent asking

  • Multi-step logins (username → next → password), iframes, SSO login hosts

  • TOTP codes

  • doctor and test <profile> commands

  • Installers for Codex CLI, Gemini CLI and Cursor; a Claude Code plugin

Development

npm install
npm test            # unit tests + end-to-end tests in a headless Chrome
npm run coverage    # fails below 98% statements/branches/functions/lines
npm run build && npm run smoke

The end-to-end tests start a throwaway headless Chrome (set CHROME_PATH if Chrome is not in a standard location). See CONTRIBUTING.md. Security reports: SECURITY.md.

License

MIT © Olgay Sezgin

Available Tools

4 tools
list_profilesList login profilesA
Read-only

Lists the configured login profiles: name, root URL and username. Passwords are never returned. Use it to pick a profile for login.

Inputs: no named parameters.

loginLog the browser tab inA

Logs the browser tab under test into its app with a locally stored profile, without revealing the credentials. Call it whenever the app shows a login form or the session expired. With Chrome remote debugging it fills the tab itself; otherwise it returns run_in_page with a one-time script for you to run in the tab.

Inputs: url, profile.

login_statusLatest login outcomeA
Read-only

Returns the latest login outcome per profile (as reported by the page in bridge mode). Use it when running the run_in_page script failed or returned nothing.

Inputs: profile.

open_configOpen the credentials fileA

Opens the credentials file in the user's text editor so they can add or change profiles themselves. The file content is never returned.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation4/5

    Each tool targets a distinct step of the login workflow: listing profiles, performing login, checking outcome, and editing config. The only potential overlap is between `login` and `login_status`, but the description explicitly scopes `login_status` to the fallback case where the `run_in_page` script fails.

    Naming Consistency4/5

    All names use snake_case and are short and predictable, with `list_profiles`, `login_status`, and `open_config` following an action-oriented pattern. `login` alone is a bare verb without a noun complement, a minor deviation from the rest of the set.

    Tool Count5/5

    Four tools is well-matched to a narrow, single-purpose server (automated credential-based login). Every tool maps to a distinct step of the flow, with no redundant or filler operations.

    Completeness3/5

    Core login and profile-listing are covered, but profile lifecycle management is deferred entirely to `open_config` opening a text editor, so an agent cannot add, edit, or remove profiles programmatically. There is also no logout/session-invalidation or profile validation tool, leaving some dead ends.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables any MCP-compatible AI agent to drive your own Chrome browser with your existing login state, filling forms, clicking elements, fetching data, and handling captchas without API keys or re-authentication.
      335 npm
      610
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      A local MCP server that lets AI coding tools drive the real Chrome browser you already have open, so agents can read logged-in pages, click, fill forms, take screenshots, and inspect tabs, cookies, and network traffic. All communication stays on your machine, with no debugging port or manual cookie copying required.
      1 npm
      ISC
    • A
      license
      Not graded
      quality
      A
      maintenance
      A local MCP server that enables AI coding tools to drive the user's real, already-logged-in Chrome browser — reading pages, clicking, typing, navigating tabs, screenshots, and cookie, network, and storage access — without opening a remote-debugging port.
      1 npm
      ISC
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI coding tools to drive the user's real, already-logged-in Chrome through an MCP stdio interface, exposing 25 tools for navigating, clicking, typing, reading pages, taking screenshots, capturing network traffic, and accessing cookies and storage. The bundled Chrome extension talks to a local bridge instead of an open remote-debugging port, so logged-in sessions and bot-detection-proof human browsing work without extra setup.
      1 npm
      ISC