Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AGENT_OS_BASE_PATHNoBase path for all agent dataC:\agent-os
AGENT_OS_MAX_WORKERSNoMax concurrent worker processes5
AGENT_OS_LOOP_INTERVALNoCoordinator loop interval (seconds)5
AGENT_OS_STALL_THRESHOLDNoSeconds before worker is considered stuck90

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": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
statusA

Get live status: coordinator, queue counts, workers

logsB

Read real log files from the agent-os system

metricsB

Read real metrics from the metrics database

injectC

Inject a task into the pending queue

handle_stuckA

Detect stuck/failed workers, kill them, and retry

coordinatorB

Start, stop, or restart the coordinator

orchestrateB

Orchestrate a complex task: decompose, inject subtasks, monitor, return results

assertB

Run output comparison assertions on tasks or arbitrary text

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/randomchips/random_agent'

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