MYA-MCP
by Michael-1103
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Listening address. | 0.0.0.0 |
| PORT | No | Listening port inside the container. | 8000 |
| DATA_DIR | No | Directory for the SQLite databases mya.db (data) and oauth.db (clients and tokens). Mount on a persistent volume. | /data |
| LOG_LEVEL | No | Log level: DEBUG, INFO, WARNING, or ERROR. | INFO |
| PUBLIC_URL | No | Required unless ALLOW_NO_AUTH=1. Public server URL in https, without path or trailing slash (e.g. https://mya-mcp.example.org). Used as the OAuth issuer and MCP resource base. http is accepted only for localhost. | |
| MCP_PASSWORD | No | Required unless ALLOW_NO_AUTH=1. Minimum 12 characters. Password requested on the OAuth login page (/consent); it is not a static bearer token. | |
| MYA_API_BASE | No | Base URL of the MYA API (useful for tests). | https://mya.epitech.eu/api |
| ALLOW_NO_AUTH | No | Set to 1 to disable all authentication and make MCP_PASSWORD and PUBLIC_URL optional. Intended for local testing only, never in production. | 0 |
| MAX_AGE_HOURS | No | Age in hours beyond which data is considered stale and refreshed at startup. | 24 |
| MYA_SITE_BASE | No | Base URL for public destination pages. | https://mya.epitech.eu |
| MAX_DROP_PERCENT | No | A scrape that would reduce the number of destinations by more than this percentage is rejected. | 30 |
| REFRESH_HOUR_UTC | No | UTC hour (0-23) of the daily refresh. | 3 |
| MAX_FAILED_PERCENT | No | Maximum tolerated percentage of failed detailed records; beyond this the scrape is rejected. | 5 |
| SCRAPE_CONCURRENCY | No | Number of simultaneous requests to the MYA API. | 8 |
| FORWARDED_ALLOW_IPS | No | IPs of reverse proxies from which X-Forwarded-For and X-Forwarded-Proto are accepted (comma-separated list, or *). | * |
| RETRY_DELAY_MINUTES | No | Delay before retrying after a failed scrape. | 30 |
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