Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOCAL_VIBES_LANENoDefault sticky-session id, sent as the standard OpenAI user field (per-call lane overrides)
LOCAL_VIBES_MODELNoModel name on that endpointqwen3-coder:30b
LOCAL_VIBES_API_KEYNoSent as the key; local servers ignore itnot-needed
LOCAL_VIBES_BASE_URLNoOpenAI-compatible endpointhttp://localhost:11434/v1
LOCAL_VIBES_MAX_ITERSNoMax model↔tool round-trips per task25
LOCAL_VIBES_ALLOW_BASHNo0 disables the run_bash tool entirely1
LOCAL_VIBES_EXTRA_BODYNoJSON object merged into every request body — superset passthrough{}
LOCAL_VIBES_LANE_HEADERNoOptional: also send the lane under this custom header (opt-in; for header-routing servers)
LOCAL_VIBES_TEMPERATURENoDefault sampling temperature (per-call temperature overrides)0.1
LOCAL_VIBES_BASH_TIMEOUTNoPer-command timeout (seconds)120
LOCAL_VIBES_MAX_CONCURRENCYNoCohort width — concurrent delegate loops offered to the backend8
LOCAL_VIBES_TOOL_RESULT_CAPNoMax chars of any tool result fed back to the model12000

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
delegateA

Delegate a self-contained coding or research task to a LOCAL model running in its own sandboxed agent loop. USE PROACTIVELY to offload grunt work — codebase searches, boilerplate, mechanical multi-file edits, test scaffolding — instead of doing it inline. The subagent reads/edits files and runs shell commands confined to working_dir, and returns a summary plus a git change report. Give it ONE clear, self-contained task with enough context to act without follow-up questions. Safe to call multiple times concurrently; in-flight runs are bounded by LOCAL_VIBES_MAX_CONCURRENCY.

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/OpenSourceWTF/local-vibes'

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