Schema | AgentRecall

AgentRecall

Describes the environment variables required to run the server.

Name	Required	Description	Default
No arguments

Features and capabilities supported by this server

Functions exposed to the LLM to take actions

Name	Description
session_startA	[ENTRY — call FIRST, before acting] Use when the user asks to start, load, continue, resume, or open memory for a project. Set mode='lite' for a ≤500-token briefing (good for fresh conversations where the agent will pull memory on demand via recall/memory_query/skill_recall).
session_endA	[ON SAVE/EXIT — YOU must call this; nothing auto-saves] Use when the user asks to save, checkpoint, summarize, end, retain, or persist the current session. Optionally pass close_phase / open_phase to update the project pipeline narrative spine in the same call.
rememberA	[MID-SESSION WRITE — single fact/decision; saying it is not saving it] Use when the user asks to remember, store, note, or save a specific decision, fact, or insight.
recallA	[RETRIEVE — use freely, any time] Use when the user asks to recall, search, find, or look up previous memory, context, or decisions.
checkB	[MID-SESSION — safe any time; for alignment, before risky decisions] Use when the user asks to validate understanding, verify alignment, or check if their interpretation matches the human's intent.

Interactive templates invoked by user choice

Name	Description
`show_projects`	Show the AgentRecall project status board.
`start_project`	Start or resume AgentRecall memory for a project.
`save_session`	Save the current session to AgentRecall.
`arstart`	Load full project context for a new session. Call this at the beginning of every session to recall past decisions, corrections, insights, and cross-project lessons.
`arsave`	Save everything from this session — journal, palace consolidation, awareness insights. Call at the end of every productive session.
`arsaveall`	Scan all of today's sessions across all projects and save them in one consolidated pass. Use when multiple agents ran in parallel.
`recall-context`	Quickly recall everything AgentRecall knows about a topic — searches journals, palace rooms, and cross-project insights.

Contextual data attached and managed by the client

Name	Description
`Awareness`	The compounding awareness document — 200-line cap, cross-project insights, trajectory, blind spots
`Awareness State`	Structured awareness state — insights array, trajectory, blind spots, compound insights

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Goldentrii/AgentRecall-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server