Skip to main content
Glama
jaimenbell

vllm-ops-mcp

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VLLM_OPS_MCP_LIVENo1 to run real-infra smoke tests
VLLM_OPS_MCP_MODELNoserved-model-name, used in completion payloadsqwen3-14b
VLLM_OPS_MCP_BASE_URLNoOpenAI-compatible base URLhttp://127.0.0.1:8000/v1
VLLM_OPS_MCP_WSL_DISTRONoWSL distro hosting vLLMUbuntu-22.04
VLLM_OPS_MCP_RUNS_IN_WSLNo1 if this server process itself runs inside WSL2/Linux (skips the wsl -d hop); auto-detected via sys.platform
VLLM_OPS_MCP_SERVICE_UNITNosystemd unit namevllm
VLLM_OPS_MCP_NVIDIA_SMI_PATHNonvidia-smi binary overridenvidia-smi
VLLM_OPS_MCP_EXEC_SCRIPT_PATHNoWSL-side path to the serve exec script (fallback source)~/vllm-systemd-exec.sh
VLLM_OPS_MCP_SERVE_CONFIG_PATHNolocal file mirror of the exec script; if set, get_serve_config reads it directly instead of shelling into WSL as a fallback source
VLLM_OPS_MCP_DEEP_RATE_LIMIT_PER_MINNocap on check_health(deep=True) + test_completion calls/min20

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/jaimenbell/vllm-ops-mcp'

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