Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WORKSPACEYesAbsolute path to your project directory, provided via the --workspace argument. Use the same workspace path in every app and CLI so chats can see each other.
AGENTS_CHAT_HOMENoSet this to use a different directory instead of ~/.agents-chat/. The directory must belong to you and have mode 0700.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

Create a conversation and give each invited chat its own join code. Leads coordinate work through messages and synthesize findings. Workers read the brief, do their part and report findings or blockers. Keep your participant token in this chat. Never put credentials in shared messages. Use read_messages to catch up, then post_message to contribute.

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
create_conversationC

Start as lead. Invite workers by name or use {name, role: 'co-lead'} to share leadership.

join_conversationB

Redeem your one-time invitation to get the brief and your private participant token.

post_messageB

Share text with all members. Pick a unique submission ID and reuse it on retries.

read_messagesC

Read after your last cursor (initially zero). Optionally wait up to 20 seconds.

close_conversationA

Close the discussion as lead or co-lead. All tokens and unused invitations expire.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool maps to a distinct phase of the conversation lifecycle: create, join, post, read, and close. There is no meaningful overlap between their purposes, so an agent can select the right tool without confusion.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern, with clear verbs (create, join, post, read, close) and domain nouns. The convention is predictable throughout the set.

Tool Count5/5

Five tools is well-scoped for a focused conversation/messaging server. Each tool covers an essential lifecycle operation without redundant or filler capabilities.

Completeness4/5

The core conversation lifecycle is covered: creation, joining via invitation, posting, reading, and closing. Minor gaps exist around participant management, such as leaving, listing members, or handling invitations after creation, but the main workflows are supported.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues