Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOOKSPAN_ENDPOINTNoOptional endpoint for exporting benchmark traces to lookspan (e.g., http://localhost:4318/v1/traces).
INFERBENCH_CODE_EXECNoSet to 0 to disable code execution in the benchmark suite (the code prompt is omitted, not scored 0).
INFERBENCH_BENCH_ITERSNoNumber of iterations per prompt for benchmark measurement (default: 3).
INFERBENCH_BENCH_NO_WARMUPNoSet to 1 to disable the warmup pass before benchmark measurements.

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/JoniMartin27/inferbench'

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