Skip to main content
Glama
reshuibuduo

TMCRA Agent Memory

by reshuibuduo

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TMCRA_API_KEYYesYour TMCRA API key. Required for authentication.
TMCRA_AGENT_IDNoA known Agent identity for attributing records. Optional.
TMCRA_BASE_URLNoThe base URL of the TMCRA API. Defaults to https://api.tmcra.comhttps://api.tmcra.com
TMCRA_DEFAULT_SCOPENoA stable project scope to use by default. Optional.

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
tmcra_recallC

Recall bounded, prompt-ready memory evidence for one query.

tmcra_ingestC

Persist conversation messages that have already occurred.

tmcra_turn_prepareB

Recall memory and return untrusted injectable context before the host answers.

tmcra_turn_commitC

Commit the real user/assistant turn and reconcile it to terminal state.

tmcra_reconcileA

Retry durable pending records and report succeeded or dead-letter states.

tmcra_get_jobC

Inspect a TMCRA asynchronous job.

tmcra_wait_jobB

Wait for a TMCRA job to succeed, fail, or be cancelled.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3/5.0

Scored across 7 tools

Disambiguation3/5

Most tools have distinct roles, but tmcra_recall and tmcra_turn_prepare both perform memory recall, and tmcra_ingest and tmcra_turn_commit both persist conversation-related content. The descriptions clarify timing and use, but an agent could still misselect between the overlapping read/write tools.

Naming Consistency3/5

All names share the tmcra_ prefix and snake_case, but the verb pattern is inconsistent: recall/ingest/reconcile are bare verbs, get_job/wait_job are verb_noun, and turn_prepare/turn_commit are object_verb. This is readable but not a uniform convention.

Tool Count5/5

Seven tools is well-scoped for a memory/turn-lifecycle server: recall/ingest cover core memory operations, turn_prepare/turn_commit cover the turn cycle, and get_job/wait_job/reconcile support asynchronous durability. Each tool has a clear place in the workflow.

Completeness4/5

The core memory lifecycle is covered: recall, ingest, turn preparation/commit, reconciliation, and async job handling. The main gap is the lack of explicit memory update/delete/forget operations, though the system may be designed as append-only evidence.

Maintenance

ActivityMaintained
ResponsivenessNo issues