Schema | claude-dev-memory

claude-dev-memory

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LETTA_API_KEY`	Yes	Your Letta Cloud API Key
`LETTA_AGENT_ID`	No	The Agent ID to use (optional)
`LETTA_BASE_URL`	No	Letta API URL	https://api.letta.com

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}
`resources`	{}

Functions exposed to the LLM to take actions

Name	Description
memory_recallA	讀取專案的 Core Memory，取得專案上下文、學習紀錄、決策。用於：session 開始時恢復上下文，或隨時查看記憶內容。
memory_updateA	更新 Core Memory，記錄專案進度和決策。注意：Core Memory 有 ~2000 token 限制，超過時建議使用 memory_archive。
memory_archiveA	存入 Archival Memory，保存完整 spec、commit、學習紀錄。特性：無大小限制、可語意搜尋。
memory_searchB	搜尋 Archival Memory，找出相關的過去記錄。用於：遇到類似問題時參考過去的解法。
memory_statusA	查看記憶系統狀態，首次使用時自動初始化 Agent。顯示：連線狀態、Core Memory 使用量、Archival 記錄數。

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
`Core Memory`	專案的核心記憶，包含 project、learnings、decisions 三個區塊

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/miles990/claude-dev-memory'

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