Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AGENTENG_MODELNoOperator-selected model required when enabling standard or RLM engines.
AGENTENG_ENABLE_RLMNoSet to 1 to enable the RLM model engine. Disabled by default.
AGENTENG_PUBLIC_URLNoSet to your HTTPS origin for self-hosting. Used to configure allowed origins.
AGENTENG_MODEL_API_KEYNoProvider API key required when enabling standard or RLM engines.
AGENTENG_MODEL_BASE_URLNoBase URL for an OpenAI-compatible provider. Optional.
AGENTENG_OPERATOR_TOKENNoOperator bearer credential required when enabling standard or RLM engines.
AGENTENG_ENABLE_STANDARDNoSet to 1 to enable the standard model engine. Disabled by default.

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
agentengC

Discover AgentEng conferences in London and San Francisco, browse agent-engineering tools across twelve disciplines, query public facts and prepare proposals for Agent Engineering HQ.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2.3/5.0

Scored across 1 tool

Disambiguation4/5

With only one tool, there is no risk of selecting the wrong tool from a set. However, the tool's description bundles multiple distinct functions (discovering conferences, browsing tools, querying facts, preparing proposals), making its scope broad and less clearly bounded.

Naming Consistency3/5

A single tool name cannot demonstrate a consistent pattern across a set. The name 'agenteng' matches the server but is a bare noun rather than a predictable verb_noun action, which is readable but not ideal for an MCP tool.

Tool Count2/5

The server's apparent purpose spans multiple operations across conferences, tools, facts, and proposals. A single catch-all tool is too few to expose those operations clearly, forcing agents to rely on one broad interface.

Completeness1/5

The domain implies distinct lifecycle actions such as discovering, browsing, querying, and preparing proposals. The surface provides no separate operations for these tasks, leaving severe gaps for agents attempting specific workflows.

Maintenance

ActivityMaintained
ResponsivenessNo issues