Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GALAXY_BRAIN_LOG_LEVELNoThe log level for Galaxy Brain
GALAXY_BRAIN_MAX_THOUGHTSNoMaximum number of thoughts allowed
GALAXY_BRAIN_MAX_OPERATIONSNoMaximum number of operations allowed

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
start_thinking

Start a new thinking session to reason through a problem step by step. Returns a session_id to use with other thinking tools.

think

Add a thought to a thinking session. Use this to reason through a problem step by step. Set next_thought_needed=false when done.

revise

Revise a previous thought in a thinking session. Use when you realize an earlier thought was wrong or incomplete.

branch

Create a new branch to explore an alternative approach. Useful when you want to try a different direction without losing your current train of thought.

conclude

Conclude a thinking session with a final synthesis. Call this when you've finished reasoning through the problem.

execute_batch

Execute a batch of operations sequentially with variable piping. Use $results[N].path.to.value to reference previous results. Available services: python, shell, file, transform.

execute_single

Execute a single operation (convenience wrapper for execute_batch)

list_services

List available services and their methods for execute_batch

generate_plan

Generate an action plan from a completed thinking session. Converts thoughts into executable operations.

execute_plan

Execute a generated action plan

think_and_do

Complete cognitive loop in one call: think through a problem, then execute operations. The ultimate galaxy brain move.

get_session

Get the current state of a thinking session

list_sessions

List all thinking sessions

get_plan

Get a plan by ID

list_plans

List all action plans

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/For-Sunny/galaxy-brain'

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