Schema | Hugging Face MCP Server

Hugging Face MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HF_TOKEN`	No	Hugging Face token used if DEFAULT_HF_TOKEN is not set (when running with stdio transport)
`TRANSPORT`	No	The transport type to use (stdio, sse, streamableHttp, or streamableHttpJson)	streamableHttpJson
`HF_API_TIMEOUT`	No	Timeout for Hugging Face API requests in milliseconds	12500
`USER_CONFIG_API`	No	URL to use for User settings (defaults to Local front-end)
`DEFAULT_HF_TOKEN`	No	Default Hugging Face token used if no Authorization header is sent. Only set this in Development/Test environments or for local STDIO Deployments.
`MCP_PING_ENABLED`	No	Enable ping keep-alive for sessions	true
`MCP_PING_INTERVAL`	No	Interval between ping cycles (in milliseconds)	30000
`MCP_STRICT_COMPLIANCE`	No	Set to True for GET 405 rejects in JSON Mode (default serves a welcome page)
`MCP_CLIENT_CONNECTION_CHECK`	No	How often to check for stale sessions (in milliseconds)	90000
`MCP_CLIENT_CONNECTION_TIMEOUT`	No	Remove sessions inactive for this duration (in milliseconds)	300000
`MCP_CLIENT_HEARTBEAT_INTERVAL`	No	How often to check SSE connection health (in milliseconds)	30000

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

ActivityActive

ResponsivenessWithin a week