Schema | phone-agent-mcp

phone-agent-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PHONE_AGENT_WS_PORT`	No	WebSocket relay port number	7788

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }
`logging`	{}

Functions exposed to the LLM to take actions

Name	Description
run_agent_taskA	Run an AI Agent task on the connected phone. The agent will plan and execute multiple steps to achieve the goal using screen vision and touch controls.
abort_taskB	Abort the currently running Agent task.
get_task_resultA	Get the detailed result of a completed Agent task by its task ID.
get_latest_taskA	Get the most recent Agent task result from the current conversation.
take_screenshotA	Take a screenshot of the connected phone screen. Returns a PNG image.
get_device_statusA	Get information about the connected phone device (model, brand, OS version, etc.).
search_memoryB	Search the persistent memory of the phone agent by keywords. Returns semantic memories (learned experience) and/or episodic records (task history).
save_memoryB	Save a semantic memory (reusable knowledge) into the phone agent's persistent memory.
delete_memoryA	Delete one memory entry (semantic or episodic) by its id.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MobileAiUse/mcp-server'

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