Web Task runs on your own machine — the client starts it, so there is no endpoint to ping. 82 installs a week from npm.
Browser tasks, sessions, and recipes for MCP and HTTP automation.
The linked repository no longer exists on GitHub — it was deleted or made private.
We have not read this server's code yet
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет web-task-api ссылается на jojo-labs/web-task-api
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add web-task-api -- npx -y web-task-api
{
"mcpServers": {
"web-task-api": {
"args": [
"-y",
"web-task-api"
],
"command": "npx"
}
}
}
[mcp_servers.web-task-api]
command = "npx"
args = ["-y", "web-task-api"]
{
"mcpServers": {
"web-task-api": {
"args": [
"-y",
"web-task-api"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"web-task-api": {
"args": [
"-y",
"web-task-api"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
WEB_TASK_API_DATA_DIR (Optional mutable data root for web-task-api runs, sessions, profiles, and temp state. When omitted, the runtime uses a platform user-data directory instead of the ambient cwd.), WEB_TASK_API_RECIPES_DIR (Optional recipes directory override. When omitted, web-task-api reads bundled recipes from the installed package.), WEB_TASK_API_TEMP_DIR (Optional temp root override used when incoming temp env variables point at your home directory or working directory.), CLIPROXY_BASE_URL (Optional CLIProxy base URL for the cliproxy planner backend.), CLIPROXY_AUTH_TOKEN (Optional CLIProxy auth token for the cliproxy planner backend.), CLIPROXY_MODEL (Optional CLIProxy model alias for the cliproxy planner backend.), OPENCODE_BASE_URL (Optional OpenCode base URL for the opencode planner backend.), OPENCODE_MODEL (Optional OpenCode model name for the opencode planner backend.), BROWSER_USER_DATA_DIR (Optional existing Chromium/Chrome user-data directory for warmed browser state reuse.), BROWSER_CHANNEL (Optional Playwright browser channel override, for example `chrome`.), HEADLESS (Optional browser headless toggle. Set `false` to prefer a visible browser.).
The author declared them in the registry entry; get the values from the project itself.
Browser tasks, sessions, and recipes for MCP and HTTP automation.
Create and control browser sessions for web automation, testing, and AI agent tasks
MCP server for AI web browser automation using Browserbase and Stagehand
Selenium MCP server for AI agents — 41 browser automation tools with snapshots and sessions.
MCP server for browser automation with AI agent
MCP server for Zen Browser automation via WebDriver BiDi
AI-powered browser automation MCP — 6 tools for web interaction, extraction, and validation.
MCP server for browser automation via Vercel's agent-browser CLI
Answers built from our own checks of this server.