Call Transcripts MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_TOKEN | Yes | Random 64-character token used in the MCP connector URL and to authenticate access to transcripts. | |
| BATCH_SIZE | No | Number of recordings processed per 5-minute run; keep equal to `MAX_FILES_PER_RUN` in `Code.gs`. | 10 |
| OPENAI_API_KEY | Yes | OpenAI API key (sk-...) used for transcription. | |
| RETENTION_DAYS | No | How long transcripts stay searchable, in days. | 120 |
| DRIVE_FOLDER_ID | No | Google Drive folder ID for the Cube ACR recordings, used in the no-Apps-Script service-account mode. | |
| TRANSCRIBE_MODEL | No | Transcription model to use. `gpt-4o-mini-transcribe` is about half the price. | gpt-4o-transcribe |
| TRANSCRIBE_LANGUAGE | No | ISO-639-1 code of your calls' language. | he |
| GOOGLE_SERVICE_ACCOUNT_JSON | No | Google 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
| 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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues