Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ICHNOS_MOCKNo1 for offline mock, 0 for real LLM calls. Required when a key is present.1
GEMINI_API_KEYNoGoogle Gemini API key for live mode. Set this or OPENROUTER_API_KEY to enable real LLM calls.
ICHNOS_PROVIDERNoProvider to use: 'gemini' or 'openrouter'. Inferred from whichever key exists if not set.
ICHNOS_ANT_MODELNoOverride the default cheap scout model.
ICHNOS_STIGMERGYNo1 for trail-following (default), 0 for static ranking A/B.1
ICHNOS_DEBUG_ANTSNo1 to print client and raw text for the first few ants.0
OPENROUTER_API_KEYNoOpenRouter API key for live mode. Set this or GEMINI_API_KEY to enable real LLM calls.
ICHNOS_PROSECUTOR_MODELNoOptional separate model for Stage 8 verification.

Capabilities

Features and capabilities supported by this server

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

Tools

Functions exposed to the LLM to take actions

NameDescription
locate_bug_tool

Locate the files most likely responsible for a bug, via a stigmergic ant-swarm search over the repo. Returns a markdown HOT/WARM/COLD heatmap with per-file evidence and, for HOT files, adversarial verification notes. This is a suggestion to prioritize reading, not a verdict -- always read the flagged files yourself before concluding.

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/Sharann-del/Ichnus'

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