Skip to main content
Glama
Call Transcripts MCP

Call Transcripts MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_TOKENYesRandom 64-character token used in the MCP connector URL and to authenticate access to transcripts.
BATCH_SIZENoNumber of recordings processed per 5-minute run; keep equal to `MAX_FILES_PER_RUN` in `Code.gs`.10
OPENAI_API_KEYYesOpenAI API key (sk-...) used for transcription.
RETENTION_DAYSNoHow long transcripts stay searchable, in days.120
DRIVE_FOLDER_IDNoGoogle Drive folder ID for the Cube ACR recordings, used in the no-Apps-Script service-account mode.
TRANSCRIBE_MODELNoTranscription model to use. `gpt-4o-mini-transcribe` is about half the price.gpt-4o-transcribe
TRANSCRIBE_LANGUAGENoISO-639-1 code of your calls' language.he
GOOGLE_SERVICE_ACCOUNT_JSONNoGoogle service account key JSON, used in the no-Apps-Script service-account mode.

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