Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OMP_NUM_THREADSNoSet to '1' on Apple Silicon to prevent FAISS segfaults.
CAUSALPFN_DEVICENoForce device: 'cpu', 'cuda:0', or 'auto' (auto-detects GPU).auto
CAUSALPFN_MAX_CONTEXTNoMax context length for CausalPFN transformer.4096
CAUSALPFN_MAX_DATASETNoMax dataset size before subsampling.1000000

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/mohitkr/causalMCP'

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