Skip to main content
Glama
TheManchineel

Jupyter Terminal MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JUPYTER_URLNoURL of the JupyterLab server (e.g., https://myjupyterserver.example.com/user/my-user/lab)
CHROMEDRIVERNoPath to chromedriver executable (optional if on PATH)
JUPYTER_TOKENNoJupyter API token (required for non-browser mode)
JUPYTER_USERNAMENoJupyter username (optional, derived from URL if omitted)
JUPYTER_VERIFY_TLSNoWhether to verify TLS certificates (default: true)true
JUPYTER_CHROME_BINARYNoPath to Google Chrome binary (optional)
JUPYTER_CONNECT_TIMEOUTNoConnection timeout in seconds (default: 10)10
JUPYTER_MCP_SOCKET_HOSTNoHost for the socket-client to connect (default: 127.0.0.1)127.0.0.1
JUPYTER_MCP_SOCKET_PORTNoPort for the socket-client to connect (default: 8765)8765
JUPYTER_BROWSER_KEEP_OPENNoWhether to keep Chrome open when daemon exits (default: false)false
JUPYTER_WEBSOCKET_RETRIESNoNumber of websocket retries (default: 3)3
JUPYTER_CHROME_USER_DATA_DIRNoPath to Chrome user data directory (optional)
JUPYTER_WEBSOCKET_RETRY_DELAYNoDelay between websocket retries in seconds (default: 1)1
JUPYTER_CHROME_PROFILE_DIRECTORYNoChrome profile directory inside user data dir (default: Default)Default

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TheManchineel/jupyter-terminal-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server