Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOCAL_CODER_MODELNoModel name to use when calling the local model server. Defaults to the model name configured in the example.default_model
LOCAL_CODER_API_KEYNoAPI key (if required) for the local model server. Defaults to 'local'.local
LOCAL_CODER_BASE_URLNoBase URL of the OpenAI-compatible local model server. Defaults to http://127.0.0.1:8080/v1.http://127.0.0.1:8080/v1
ALLOWED_WORKSPACE_ROOTNoThe directory tree the worker is allowed to edit. Set this or ALLOWED_WORKSPACE_ROOTS so the requested workspace is inside an approved directory.
ALLOWED_WORKSPACE_ROOTSNoColon-separated list of directory trees the worker is allowed to edit. Use as an alternative to ALLOWED_WORKSPACE_ROOT for multiple roots (supported on macOS/Linux).
LOCAL_CODER_ENABLE_THINKINGNoSet to 'false' to disable thinking/reasoning output from the model. Useful when the model returns no usable text.true

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
delegate_to_local_coderB

Delegate a coding implementation task to the local Qwen worker.

The worker can inspect project files, patch code, create files, run tests, and inspect git diff. Codex should review the result afterwards.

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/starmania7/local-coder-mcp-agent'

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