# Cursor Membase

> Membase plugin for Cursor — persistent memory with MCP, session hooks, and always-on rules

- **Type:** MCP server
- **Install:** `agentstack add mcp-aristoapp-cursor-membase`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [aristoapp](https://agentstack.voostack.com/s/aristoapp)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [aristoapp](https://github.com/aristoapp)
- **Source:** https://github.com/aristoapp/cursor-membase

## Install

```sh
agentstack add mcp-aristoapp-cursor-membase
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

Membase Plugin for Cursor

  

  Persistent long-term memory for Cursor — hybrid vector search + knowledge graph.

  
  
  

  Website · Docs · Dashboard · Issues

---

Give your [Cursor](https://cursor.com) agent persistent memory that survives across sessions. Membase uses hybrid vector search + knowledge graph to remember not just text, but entities, relationships, and facts.

> **Free to start** — Sign up at [app.membase.so](https://app.membase.so) and connect in under a minute.

## Install

Install from the [Cursor Marketplace](https://cursor.com/marketplace), then click **Connect** next to the Membase MCP server in Cursor settings to complete OAuth. No CLI, no API keys — one click and you're done.

## What It Does

```txt
┌─────────────────────────┐
│  AI Session             │  Agent uses search_memory, add_memory,
│                         │  search_wiki, add_wiki, etc.
└───────────┬─────────────┘
            ▼
┌─────────────────────────┐
│  Membase MCP Server     │  Remote server at mcp.membase.so
│  (streamable HTTP)      │  OAuth handled by Cursor
└───────────┬─────────────┘
            ▼
┌─────────────────────────┐
│  Membase Backend        │  Hybrid vector search + knowledge graph
│                         │  Entity/relationship extraction
└─────────────────────────┘
```

- **Always-on rule** — Instructs the agent to proactively use Membase MCP tools.
- **Knowledge graph** — Unlike simple vector-only memory, Membase stores entities, relationships, and facts. Search results include related nodes and edges for richer context.

## MCP Tools

### Memory (personal context)

| Tool | Description |
| --- | --- |
| `search_memory` | Semantic search across memories. Supports date filtering (`date_from`, `date_to`), source filtering (`sources` — e.g. `['slack', 'gmail']`), and project scoping. |
| `add_memory` | Store durable personal context — preferences, decisions, goals, architecture choices. |
| `get_current_date` | Get current date/time in user's timezone for anchoring date-range searches. |

### Wiki (factual knowledge)

| Tool | Description |
| --- | --- |
| `search_wiki` | Hybrid keyword + semantic search for documents, references, and stable knowledge. |
| `add_wiki` | Create a wiki document (markdown with `[[wikilinks]]`). Optional auto-summarize. |
| `update_wiki` | Update an existing wiki document by ID. |
| `delete_wiki` | Permanently delete a wiki document by ID. |

### Resources

| Resource | Description |
| --- | --- |
| `membase://profile` | User settings — display name, role, interests, timezone. |
| `membase://recent` | Recent memories timeline (top 10). |

## How Membase Differs

| | Simple vector memory | **Membase** |
| --- | --- | --- |
| **Storage** | Flat embeddings | Hybrid: vector embeddings + knowledge graph |
| **Search** | Vector similarity only | Vector + graph traversal (entities, relationships, facts) |
| **Extraction** | Store raw text | AI-powered entity/relationship extraction |
| **Knowledge** | Single store | Separate memory (personal) + wiki (factual knowledge) |
| **Auth** | API key | OAuth 2.0 with PKCE (no secrets to manage) |
| **Integrations** | None | Google Calendar, Gmail, Slack, Notion sync |

## Links

- [Membase](https://membase.so/?utm_source=github&utm_medium=cursor-membase) — Website
- [Dashboard](https://app.membase.so) — Manage your memories
- [Docs](https://docs.membase.so) — Full documentation
- [Cursor](https://cursor.com) — AI code editor

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [aristoapp](https://github.com/aristoapp)
- **Source:** [aristoapp/cursor-membase](https://github.com/aristoapp/cursor-membase)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-aristoapp-cursor-membase
- Seller: https://agentstack.voostack.com/s/aristoapp
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.