本文へ移動
cccskills
無料GitHub で公開

bdb-memb-mcp

Model Context Protocol interface to the memB persistent agent memory layer. Use when an agent needs to add, search, list or delete persistent memories locally and offline. Exposes add_memory, search_memory, list_memories and delete_memory.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

BDB memB Persistent Memory MCP Server

The memb-mcp server provides a standard Model Context Protocol (MCP) interface to the memB persistent agent memory layer. It allows any compatible developer agent (such as Cursor, Google Antigravity, Claude Code, or VS Code Cline) to read, write, and query persistent memories locally and offline.


🛠️ MCP Server Specifications

  • Server Name: memb-mcp
  • Command: __MCPS_DIR__/memb-mcp/.venv/bin/python (macOS/Linux) or __MCPS_DIR__/memb-mcp/.venv/Scripts/python.exe (Windows)
  • Arguments: ["__MCPS_DIR__/memb-mcp/run.py"]
  • Environment Variables:
    • MEMB_DATA_DIR: Path to the SQLite database and config folder (defaults to ~/.MemBDB).
    • GEMINI_API_KEY: User Google API key for reasoning.

🔌 Exposed MCP Tools

1. add_memory

Saves a new fact, coding preference, or workaroud to the local SQLite database.

  • Parameters:
    • text (string, required): The fact or guideline to store.
    • user_id (string, optional): Owner of the row. Default: env MEMB_USER_ID (fallback $USER). Pass a group id from MEMB_GROUP_IDS only to write a shared group row on purpose.
    • category (string, optional): Default project_card when project_id is set, else task_learnings. Options: project_card, architecture_decisions, bug_fixes, coding_conventions, tooling_setup, anti_patterns, task_learnings, user_preferences, dependency_decisions, performance_findings, security_constraints, testing_patterns, data_model, api_contracts, deployment_runbook, team_norms, domain_glossary, godmode.
    • project_id (string, optional): Active workspace folder to isolate search queries.
    • source, harness, session (string, optional): Provenance, stored in the row metadata.

2. search_memory

Queries both global godmode memory and the active project_id memories in parallel, returning semantic matches ranked by cosine similarity.

  • Parameters:
    • query (string, required): Keyword or semantic question.
    • user_id (string, optional): Restrict to one owner id. Default: the user plus the group ids in MEMB_GROUP_IDS (default bdb_developer).
    • limit (integer, optional, default: 5): Maximum matching memories to return.
    • project_id (string, optional): Active workspace folder.

3. list_memories

Lists all memories currently registered in the database for the active user.

  • Parameters:
    • user_id (string, optional): Restrict to one owner id. Default: the user plus MEMB_GROUP_IDS.
    • limit (integer, optional, default: 50): Maximum results.

4. delete_memory

Deletes a specific memory segment using its UUID.

  • Parameters:
    • memory_id (string, required): The unique UUID of the memory item.

🔒 Security Hardening

The memb-mcp server has no automatic credential filter today: it stores whatever an agent sends it.

  • Never ingest credentials: API keys (Google Cloud, OpenAI, GitHub, etc.), plaintext passwords, database URLs.
  • The protection is the rule in this skill (and in memb-skill) plus human review of stored memories.
  • An automatic pre-ingestion filter is planned but not released.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

hybridlabor-api のスキルをすべて見る

このスキルの問題を報告する