---
title: "contextdb-memory"
description: "Customer memory with recall, confirmation, forgetting, and pre-action evidence checks."
canonical: https://agentpluginsdirectory.com/plugins/contextdb-memory
last-updated: 2026-10-12
---

# contextdb-memory
Customer memory with recall, confirmation, forgetting, and pre-action evidence checks.
- Slug: contextdb-memory
- Publisher: Atoms AI
- Repository: https://github.com/atomsai/contextdb-mcp-plugin
- Manifest: plugin.json
- Version: 1.1.1
- License: Apache-2.0
- Category (editorial): other
- Skills: 1 (contextdb-compaction)
- MCP servers: 1 (contextdb)
- Stars: 0
- Repository created: 2026-09-22
- Repository last pushed: 2026-10-12
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/contextdb-memory
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What contextdb-memory does, in the publisher's words

ContextDB is an OAuth MCP connector that gives ChatGPT, Claude, Cursor, Grok, Lovable, and other MCP clients six scoped customer-memory tools. It remembers sourced facts, recalls context, checks evidence before actions, records confirmation, and forgets selected memory without exposing a project-wide API key to the client.

The old workflow copied a server credential into every AI client and let the caller choose arbitrary customer partition IDs. ContextDB OAuth grants instead bind one account, project, scope set, and opaque memory partition on the server.

Or add the remote server manually:

- remember
- recall
- recall_for_action
- pending_confirmations
- confirm
- forget

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/atomsai/contextdb-mcp-plugin/HEAD/README.md

## MCP servers

- contextdb: transport: streamable-http; url: https://api.contextdb.ai/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.