Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoJunos MCP Server host. Passed via -H/--host. Do not use with stdio transport.
PORTNoJunos MCP Server port. Passed via -p/--port. Default is 30030.
TRANSPORTNoJunos MCP Server transport (e.g., stdio, streamable-http). Passed via -t/--transport. Default is streamable-http.
TOKENS_FILENoPath to the .tokens file for authentication (streamable-http transport only). Defaults to .tokens alongside jmcp.py.
JUNOS_TIMEOUTNoCommand timeout in seconds for Junos CLI operations.
DEVICE_MAPPINGYesThe name of the JSON file containing the device mapping (e.g., devices.json). Passed via -f/--device-mapping.
JMCP_POOL_IDLE_TIMEOUTNoIdle timeout in seconds for pooled SSH/NETCONF connections. Default: 300.300
ALLOW_UNAUTHENTICATED_HTTPNoSet to 'true' to allow streamable-http without authentication (loopback only, development only).

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

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