# Engram

> Engram is a freemium MCP server for knowledge and memory. Word-for-word, searchable memory shared across every MCP client. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $18 a month
- **Platforms:** API, Web, CLI
- **Website:** https://getengram.app
- **Repository:** https://github.com/get-engram/engram
- **MCP Registry name:** app.getengram/engram
- **Categories:** knowledge and memory
- **Listing updated:** 2026-11-15

## About

Engram saves conversations as complete transcripts instead of summaries, so an assistant can later retrieve exactly what was said. Messages, including tool calls, are stored as full text and searched by meaning with bge-base-en-v1.5 embeddings. Recognized API keys, tokens and personal data are stripped before anything is saved, and genuine secrets belong in a separate vault that is encrypted with AES-256-GCM on your own machine.

The whole service runs on Cloudflare Workers, D1, Vectorize and Workers AI, with per-organization isolation. In Claude Code you install a plugin and approve access in the browser, and the plugin includes a skill about when to search memory and what is worth saving. Other clients point at the remote URL and sign in over OAuth, and stdio-only clients can bridge with mcp-remote.

The free plan keeps 10,000 messages permanently; paid plans raise that to 1,000,000 messages, with team seats and university pricing.

## Features

- **Verbatim storage:** Keeps every message as unsummarized text, including tool calls.
- **Semantic search:** Finds past conversations by meaning rather than keywords.
- **Automatic redaction:** Strips recognized keys, tokens and personal data before saving.
- **Zero-knowledge vault:** Secrets are encrypted on your device and kept apart from searchable memory.
- **Cross-client memory:** Save in one assistant and recall from another.
- **Team seats:** Pooled memory and multi-tenant isolation for teams.

## Good for

- Recall a decision made in an earlier coding session
- Share memory between Claude and Cursor
- Replay an agent workflow to debug it
- Search months of conversations for a past deployment
- Give a team one pooled memory

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http engram https://mcp.getengram.app/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.getengram.app/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "engram": {
      "url": "https://mcp.getengram.app/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "engram": {
      "type": "http",
      "url": "https://mcp.getengram.app/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "engram": {
      "serverUrl": "https://mcp.getengram.app/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "engram": {
      "type": "http",
      "url": "https://mcp.getengram.app/mcp"
    }
  }
}
```

## Tools

- `create_conversation`: Starts a conversation with optional title, tags and metadata.
- `append_messages`: Adds messages to an existing conversation.
- `search`: Searches all conversations by meaning.
- `get_conversation`: Retrieves a conversation with its messages.
- `list_conversations`: Lists conversations with filtering and pagination.
- `delete_conversation`: Removes a conversation and its data.
- `memory_status`: Shows how much of the plan's storage is used.
- `whoami`: Shows which Engram account the connection uses.

## FAQ

### Is there a free plan?

Yes: 10,000 messages of permanent memory, unlimited conversations, one seat, MCP and REST access and export.

### How do I install it in Claude Code?

Run /plugin marketplace add get-engram/engram then /plugin install engram@engram, and approve access in the browser.

### Are conversations summarized?

No. Messages are stored verbatim, apart from redacted secrets and personal data.

### Where does it run?

On Cloudflare Workers, D1 and Vectorize.

### Is there a student discount?

Yes. A verified university email gets the Pro or Team plan for $3 per seat.

### Is Engram free?

Engram has a free plan, with paid plans for more usage or features. Paid plans start at $18 a month.

### How do I add Engram to Claude Code?

Run this command in your terminal: claude mcp add --transport http engram https://mcp.getengram.app/mcp

### What are the best alternatives to Engram?

The closest alternatives to Engram are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [MedXpert 图书馆连接器（通用版）](https://ai-powered.com/mcp/medxpert): MedXpert 图书馆连接器（通用版） is an open-source MCP server for knowledge and memory.
- [Context Nest](https://ai-powered.com/mcp/context-nest): Context Nest is a freemium MCP server for knowledge and memory.
- [Tulsa Ecosystem Map](https://ai-powered.com/mcp/tulsa-ecosystem-map): Tulsa Ecosystem Map is a free MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/engram
