Skip to main content
Glama
phonebridge
by iantinney

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TW_OCR_PYTHONNoPath to a Python interpreter that has `rapidocr_onnxruntime` installed. Used for OCR when teaching from an uploaded screen recording or for tasks stored without screen text.
TW_TEACH_MODELNoOptional model to interpret recorded steps. Use `claude-plan` for your signed-in `claude` CLI, or `local:<url>` for a local model. Off by default.off
PHONEBRIDGE_VLMNoOptionally enables a model to name unfamiliar screens. Use `claude-cli` to use your signed-in `claude` CLI (and AWS Bedrock on its usage limit, with `uv sync --extra vlm` and AWS credentials), or `bedrock` to use Bedrock only. Off by default.off
TW_PHONE_ACCOUNTSNoJSON mapping of phone alias to required account, e.g. '{"phone": "ig:me"}'. Missions stop unless the specified account is signed in.
TW_ACCOUNT_HANDLESNoJSON mapping of account id to handle, e.g. '{"ig:me": "your_handle"}'.

Instructions

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.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources