Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ANTHROPIC_API_KEYYesAnthropic API key for agent LLM calls

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
nero_spawnA

Create a new named persistent agent. The agent stays alive in memory with full conversation history until killed.

nero_askA

Send a message to a persistent agent and receive its response. The agent remembers all prior conversation. It can use tools (read files, search, run commands) to do real work.

nero_broadcastA

Send a message to all agents (or a filtered subset by tags). Optionally collect all responses.

nero_statusA

Get an overview of the agent pool, or detailed status for a specific agent.

nero_memory_writeA

Write a key-value entry to the shared memory bus. All agents and Master Control can read it.

nero_memory_readA

Read entries from the shared memory bus. Can read a specific key, all keys with a prefix, or all entries.

nero_memory_dumpA

Export memory bus entries matching a prefix to a JSON file on disk. Use for pipeline recovery, monitoring, and reports.

nero_killA

Terminate a named agent. Its conversation history and context are permanently destroyed.

nero_resetB

Clear an agent's conversation history and token counter, but keep the agent alive with its configuration intact.

nero_configureA

Update an agent's configuration at runtime (model, history limit, token limit, system prompt, tags).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4/5.0

Scored across 10 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: interacting with agents, managing memory, configuring, spawning, killing, resetting, and status. No two tools overlap in functionality.

Naming Consistency5/5

All tools follow the consistent prefix 'nero_' and use a verb_noun pattern (e.g., nero_spawn, nero_kill, nero_memory_read). No mixing of conventions.

Tool Count5/5

With 10 tools, the set is well-scoped for managing persistent agents and a shared memory bus. Each tool serves a necessary role without redundancy.

Completeness5/5

The tools cover the full lifecycle of agents (create, configure, interact, reset, kill) and shared memory (read, write, dump). No obvious gaps in the intended functionality.

Maintenance

ActivityInactive
ResponsivenessNo issues