EngrAmo MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_BIND_ADDR | No | http mode only — bind address for http mode. | 0.0.0.0:8080 |
| MCP_PUBLIC_URL | No | http mode only — this deployment's own public URL (bare origin, no path — the endpoint is served at /), e.g. https://mcp.engramo.app. Also allowlists that host for inbound requests; without it, every request is rejected (see MCP_ALLOWED_HOSTS). | |
| ENGRAMO_API_URL | No | Base URL of the EngrAmo API. Defaults to https://api.engramo.app (production). Dev is https://api-engram.volmyr.com. Dev and prod are separate backends with separate accounts — the token must be minted from the same environment. | https://api.engramo.app |
| ENGRAMO_API_TOKEN | Yes | Your EngrAmo API token, generated from Settings → API Tokens. Required for the stdio (locally launched) transport; unused in http mode, where each session supplies its own token via an Authorization: Bearer header (or OAuth). | |
| ENGRAMO_TTS_MODEL | No | stdio only. Gemini TTS model id. | gemini-3.8-flash-tts |
| ENGRAMO_TTS_VOICE | No | stdio only. Default voice used when a generate_card_audio call doesn't specify one. | Puck |
| MCP_ALLOWED_HOSTS | No | http mode only — extra comma-separated hostnames/host:port values to permit, on top of the one derived from MCP_PUBLIC_URL. Only needed for extra entry points (e.g. a Cloud Run service's own *.run.app fallback URL alongside its custom domain). | |
| ENGRAMO_TTS_PROVIDER | No | stdio only. TTS engine selector. Only gemini is supported today; an unrecognized value fails startup. | gemini |
| ENGRAMO_ENABLE_PAID_AI | No | Gates the paid generate_tts_for_cards tool, which spends EngrAmo's own metered TTS quota (as opposed to generate_card_audio, which spends your own Gemini key/quota). | |
| ENGRAMO_TTS_GEMINI_API_KEYS | No | stdio only. Your own Gemini API key, or a comma-separated list of keys (tried in random order for rotation). Enables the list_tts_voices and generate_card_audio tools. Unset by default, which means the TTS tools are absent. Ignored (with a startup warning) in http 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
ActivityActive
ResponsivenessResponsive