Schema | web-gpt-file-save

web-gpt-file-save

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_HOST`	No	Address to bind. For tunnel scenarios, use 127.0.0.1.
`MCP_PORT`	No	Port to listen on. Default: 8765.	8765
`FILE_SAVE_ROOT`	Yes	The unique filesystem root directory where files are allowed to be saved.
`MCP_QUICK_PORT`	No	Port for Quick mode. Default: 8765.	8765
`MCP_STATE_FILE`	No	Path to the OAuth state file. Default: .web-gpt-file-save/oauth-state.json.	.web-gpt-file-save/oauth-state.json
`MCP_STABLE_PORT`	No	Port for Stable mode. Default: 8878.	8878
`MCP_AUTH_PASSWORD`	Yes	Password for local single-user OAuth authorization. Must be at least 12 characters.
`MCP_MAX_FILE_BYTES`	No	Maximum file download size in bytes. Default: 25 MiB.	25 MiB
`MCP_PUBLIC_BASE_URL`	No	The public HTTPS base URL for this service. In Quick mode this is auto-generated; in Stable mode it is read from local settings.
`MCP_ALLOW_INSECURE_HTTP`	No	Set to '1' to allow loopback HTTP for local development.
`MCP_DOWNLOAD_TIMEOUT_MS`	No	Single download timeout in milliseconds. Default: 30000 ms.	30000
`MCP_ACCESS_TOKEN_TTL_SECONDS`	No	Access token lifetime in seconds. Default: 3600 seconds.	3600

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessNo issues