Skip to main content
Glama
LvcidPsyche

Auto-Browser

by LvcidPsyche
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
APP_ENVNoSet to 'production' to enable stricter security requirements.
GEMINI_API_KEYNoAPI key for Google Gemini provider.
OPENAI_API_KEYNoAPI key for OpenAI provider.
API_BEARER_TOKENNoThe bearer token used to protect the controller API.
CLAUDE_AUTH_MODENoSet to 'cli' to use subscription-backed CLI auth for Anthropic.
GEMINI_AUTH_MODENoSet to 'cli' to use subscription-backed CLI auth for Gemini.
MCP_TOOL_PROFILENoThe tool surface to expose. Set to 'full' for the entire legacy/internal tool surface. Default is curated.
OPENAI_AUTH_MODENoSet to 'cli' to use subscription-backed CLI auth instead of API keys.
ANTHROPIC_API_KEYNoAPI key for Anthropic/Claude provider.
MCP_ALLOWED_ORIGINSNoComma-separated list of exact allowed origins for MCP browser clients.
REQUIRE_OPERATOR_IDNoSet to 'true' if every non-health request must carry an operator ID header.
AUTO_BROWSER_BASE_URLYesThe base URL where the Auto Browser FastAPI server is running (e.g., http://127.0.0.1:8000/mcp).
AUTH_STATE_ENCRYPTION_KEYNoA 44-char Fernet key used for encrypting auth-state storage at rest.
AUTO_BROWSER_BEARER_TOKENNoBearer token for authenticating the bridge with the Auto Browser API.
REQUIRE_AUTH_STATE_ENCRYPTIONNoWhether to force encryption for auth state files.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}
resources
{
  "subscribe": false
}
experimental
{
  "autoBrowser": {
    "workflowProfiles": [
      "fast",
      "governed"
    ],
    "resumableAgentJobs": true,
    "cancellableAgentJobs": true,
    "discardableAgentJobs": true
  }
}

Tools

Functions exposed to the LLM to take actions

NameDescription
browser.create_sessionC

Create a new browser session and optionally navigate to a start URL.

browser.save_memory_profileA

Save a named memory profile with context from the current session. Loaded into future sessions via memory_profile=name in create_session.

browser.get_memory_profileB

Retrieve a saved memory profile by name.

browser.list_memory_profilesB

List all saved memory profiles.

browser.list_sessionsB

List live and persisted browser sessions.

browser.get_sessionC

Get one browser session summary.

browser.observeC

Capture the current browser observation with screenshot, interactables, and perception summary.

browser.screenshotB

Capture a lightweight screenshot for one session without the full observe payload.

browser.get_consoleC

Read recent browser console messages for an active session.

browser.get_page_errorsB

Read recent uncaught page errors for an active session.

browser.get_request_failuresC

Read recent failed network requests for an active session.

browser.stop_traceB

Finalize the current Playwright trace for an active session and return its artifact path.

browser.list_auth_profilesA

List reusable saved auth profiles that can be loaded into a new session.

browser.get_auth_profileB

Inspect one saved auth profile and its storage-state metadata.

browser.list_downloadsC

List files captured from browser downloads for one session.

browser.list_tabsB

List currently open tabs/pages for one session.

browser.activate_tabC

Switch the active session page to one tab index.

browser.close_tabC

Close one tab index if more than one tab is open.

browser.execute_actionC

Execute one browser action using the shared internal action schema.

browser.save_auth_profileB

Save the current session storage state into a reusable named auth profile.

browser.request_human_takeoverC

Ask for a human to take over the shared browser desktop.

browser.close_sessionB

Close a session and finalize its trace/artifacts.

browser.readiness_checkA

Run a deployment readiness check. Returns pass/warn/fail for encryption, operator identity, bearer token, session isolation, Witness audit, host allowlist, PII scrubbing, and upload approval. Pass mode='confidential' for stricter checks.

browser.get_network_logA

Return captured HTTP request/response entries for a session. Filtered by method (GET/POST/...) or URL substring. All sensitive headers and bodies are automatically PII-scrubbed.

browser.fork_sessionA

Fork a session: snapshot its cookies, storage state, and current URL, then create a new independent session with that state. Useful for branching workflows or running parallel variants.

browser.eval_jsB

Execute a JavaScript expression in the current page context and return the result. Use for DOM queries, value extraction, or lightweight scripting that has no dedicated tool.

browser.wait_for_selectorB

Wait for a CSS selector to reach a specific state (visible, hidden, attached, detached). Returns when the condition is met or raises on timeout.

browser.get_htmlA

Get the HTML source of the current page. Set text_only=true to strip tags and return plain text. Set full_page=false (default) for visible viewport only.

browser.find_elementsA

Find all elements matching a CSS selector and return their text, href, value, bounding box, and visibility. Useful before clicking or scraping multiple items.

browser.drag_dropA

Drag from one element or coordinate to another. Provide source_selector OR (source_x, source_y), and target_selector OR (target_x, target_y).

browser.set_viewportC

Resize the browser viewport to the specified width and height.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
Active SessionsList of all active browser sessions

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LvcidPsyche/auto-browser'

If you have feedback or need assistance with the MCP directory API, please join our Discord server