Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MOLTALK_OFFLINENoSet to 1 to turn off PubChem network lookups (each new molecule's InChIKey is otherwise sent to PubChem, cached).
MOLTALK_WORKERSNoNumber of RDKit worker processes (default 2).
MOLTALK_TIMEOUT_SNoPer-call timeout in seconds for RDKit work (default 20 s; the worker is killed when exceeded).
MOLTALK_MAX_QUEUEDNoMaximum number of queued requests (default 16).
MOLTALK_ALLOWED_HOSTSNoIn HTTP mode, additional accepted Host values (DNS-rebinding protection). Only localhost/127.0.0.1/[::1] are accepted unless set.
MOLTALK_MAX_BODY_BYTESNoMaximum HTTP request body size in bytes (default 64 KB).
MOLTALK_ALLOWED_ORIGINSNoIn HTTP mode, additional accepted Origin values. Only localhost/127.0.0.1/[::1] are accepted unless set.
MOLTALK_WORKER_MEMORY_MBNoAddress-space cap in MB for each RDKit worker (default 2 GB).

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