waha-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port. | 3000 |
| DATA_DIR | No | OAuth state (auth.db), message cache (cache.db), media secret. | /data |
| TIMEZONE | No | IANA time zone for dates and day boundaries (e.g. America/Lima). | UTC |
| WAHA_API_KEY | Yes | WAHA API key. Also the OAuth login secret. | |
| WAHA_API_URL | Yes | Base URL of WAHA (internal URL when deployed next to it). | |
| WAHA_SESSION | No | WAHA session name. | default |
| CACHE_ENABLED | No | Keep a SQLite copy of read messages in DATA_DIR/cache.db. | true |
| MEDIA_MAX_BYTES | No | Largest file served by /media/:token (100 MiB). | 104857600 |
| PUBLIC_BASE_URL | Yes | Public HTTPS URL of this server (http only for localhost). | |
| CACHE_MAX_AGE_DAYS | No | Prune cached messages older than N days (0 keeps them forever). | 0 |
| STATS_MAX_MESSAGES | No | Per-chat message cap; fan-out tools read up to 100 chats each. | 5000 |
| CACHE_REFRESH_HOURS | No | Each sync re-reads this window before the newest cached message. | 48 |
| TRANSCRIPTION_MODEL | No | Transcription model id (e.g. openai/whisper-large-v3-turbo). Must be set together with TRANSCRIPTION_API_URL and TRANSCRIPTION_API_KEY. | |
| TRANSCRIPTION_API_KEY | No | API key of the transcription provider. Must be set together with TRANSCRIPTION_API_URL and TRANSCRIPTION_MODEL. | |
| TRANSCRIPTION_API_URL | No | OpenAI-compatible speech-to-text base URL (e.g. https://openrouter.ai/api/v1). Transcription is off unless TRANSCRIPTION_API_URL, TRANSCRIPTION_API_KEY and TRANSCRIPTION_MODEL are all set (setting only some of them is a startup error). | |
| MEDIA_INLINE_MAX_BYTES | No | Largest file returned inline (5 MiB); larger ones get a link. | 5242880 |
| MEDIA_LINK_TTL_SECONDS | No | Lifetime of signed media links. | 600 |
| TRANSCRIPTION_LANGUAGE | No | Language hint, lowercase ISO 639-1/639-2 code (e.g. es); omit to auto-detect. | |
| TRANSCRIPTION_MAX_SECONDS | No | Longer voice notes are not transcribed automatically. | 300 |
| TRANSCRIPTION_MAX_PER_CALL | No | New automatic transcriptions per tool call (0 = only the transcribe_audio tool). | 20 |
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 issues