Schema | blop

blop

Overview Schema Related Servers Score Discussions

Server Configuration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`BLOP_ENV`	No	Environment mode (production enables stricter validation expectations)	development
`LOGIN_URL`	No	Where blop navigates to log in
`APP_BASE_URL`	No	Default app URL (used as fallback if no URL passed to tools)
`BLOP_DB_PATH`	No	Where blop stores its database	.blop/runs.db
`BLOP_HEADLESS`	No	false = show browser window during tests (useful for debugging)	true
`TEST_PASSWORD`	No	Login password
`TEST_USERNAME`	No	Login email/username
`BLOP_API_TOKEN`	No	Blop Cloud API token
`BLOP_DEBUG_LOG`	No	JSON log destination path	.blop/blop.log
`BLOP_MAX_STEPS`	No	Max steps the AI agent takes per flow	50
`GOOGLE_API_KEY`	Yes	Gemini API key. Get one free at aistudio.google.com
`BLOP_HOSTED_URL`	No	Blop Cloud sync URL
`BLOP_PROJECT_ID`	No	Blop Cloud project ID
`COOKIE_JSON_PATH`	No	Path to exported browser cookies (JSON array)
`BLOP_ALLOWED_HOSTS`	No	Optional host allowlist for app_url validation
`BLOP_SPA_SETTLE_MS`	No	Extra settle time in ms after SPA navigation	1500
`STORAGE_STATE_PATH`	No	Path to a saved Playwright session (for SSO/OAuth)
`BLOP_COMPAT_HEADLESS`	No	Run compatibility browser session headless or headed	true
`BLOP_RUN_TIMEOUT_SECS`	No	Total run timeout in seconds (0 disables timeout)	0
`BLOP_COMPAT_OUTPUT_DIR`	No	Where compatibility artifacts (snapshots/screenshots/storage-state files) are written	.playwright-mcp
`BLOP_NETWORK_IDLE_WAIT`	No	Seconds to wait for network idle after page load	2.0
`BLOP_STEP_TIMEOUT_SECS`	No	Per-step replay timeout in seconds	45
`TEST_PASSWORD_SELECTOR`	No	CSS selector for the password input field	auto-detected
`TEST_USERNAME_SELECTOR`	No	CSS selector for the username input field	auto-detected
`BLOP_AGENT_MAX_FAILURES`	No	Max recoverable action failures before agent aborts recording	profile-driven
`BLOP_ALLOW_INTERNAL_URLS`	No	Block private/internal app URLs unless explicitly enabled	false
`BLOP_DISCOVERY_MAX_PAGES`	No	Default crawl page cap for discovery tools	profile-driven
`BLOP_ENABLE_COMPAT_TOOLS`	No	Registers legacy/compat MCP tool surface when true	false
`BLOP_EXPLORATION_PROFILE`	No	Tuning preset (default or saas_marketing) for discovery and replay behavior	default
`BLOP_ALLOW_SCREENSHOT_LLM`	No	Privacy guard for visual-regression triage	false
`BLOP_CAPABILITIES_PROFILE`	No	Predefined capability profile (production_minimal, production_debug, full)	env-dependent
`BLOP_COMPAT_SNAPSHOT_MODE`	No	Snapshot mode hint for compatibility workflows	incremental
`BLOP_REQUIRE_ABSOLUTE_PATHS`	No	Require absolute paths for DB/runs/log values	false
`BLOP_COMPAT_TEST_ID_ATTRIBUTE`	No	Preferred test id attribute used when building element selectors	data-testid
`BLOP_AGENT_MAX_ACTIONS_PER_STEP`	No	Max agent actions per reasoning step during recording	profile-driven

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

Name	Description
No tools

Prompts

Interactive templates invoked by user choice

Name	Description
No prompts

Resources

Contextual data attached and managed by the client

Name	Description
No resources

Server Configuration
Capabilities
Tools
Prompts
Resources

Latest Blog Posts

Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly
Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
OpenAI
open source

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/n2400813g/blop-mcp'

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