Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TAMLIL_DB_PATHNoOverride the path to the recording database
TAMLIL_RECORDINGS_ROOTNoOverride the root directory for recordings

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
list_meetingsA

List recorded meetings, newest first.

from_date/to_date are inclusive ISO dates (YYYY-MM-DD); app filters on the
meeting app name (case-insensitive substring, e.g. "zoom").
get_meetingA

Full metadata for one meeting: roster, named speakers, transcript availability, and pending clarification count.

get_transcriptA

The meeting transcript, with resolved speaker names and clock timestamps.

By default this does NOT return the transcript text — a long meeting would
flood your context. It returns metadata plus `path`: a rendered transcript
file you should open with your own file tools, reading only the ranges you
need. To pull lines inline instead (e.g. no filesystem access), pass `limit`
(and optional `offset`) to get that slice of segment lines directly.
search_transcriptsA

Search all transcripts for a phrase (case-insensitive). Returns matching meetings, newest first, with the matching transcript lines as excerpts.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.3/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct role: list_meetings filters and lists, get_meeting fetches metadata for one meeting, get_transcript retrieves transcript content, and search_transcripts finds phrases across transcripts. No two tools overlap in purpose.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with lowercase and underscores: list_meetings, get_meeting, get_transcript, search_transcripts. The naming is uniformly readable and predictable.

Tool Count5/5

With 4 tools, the server is well-scoped for a meeting/transcript archive. Each tool covers a core operation, and the count is neither too sparse nor excessive.

Completeness5/5

The server provides a complete read-only lifecycle: list meetings, get metadata, get transcript, and search content. There are no obvious dead ends for the stated purpose of retrieving meeting recordings and transcripts.

Maintenance

ActivityStale
ResponsivenessNo issues