# MemCell

MemCell brings persistent memory, graph traversal, and document search to AI agents. It lets models check previous context before acting and score confidence.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: memcell-ai
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/memcell-ai/mcp
- Updated: 2026-10-28
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/memcell

## What it does

AI coding sessions drop context once a prompt thread finishes. MemCell fixes this limitation by exposing a structured memory layer over MCP. It supplies seven workspace tools: `recall` for fetching instructions, `remember` for saving facts, `report` and `feedback` for confidence adjustments, plus document ingestion, retrieval, and telemetry insights.

Document retrieval handles PDF, DOCX, CSV, HTML, and Markdown files. Knowledge graph queries surface one-hop connections alongside text chunks. To evaluate memory reliability, the system calculates Brier scores and calibration curves.

Setup takes one command. For offline tasks without network access, running `memcell start --daemon` spins up an embedded PGlite vector engine locally on port 3000.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://memcell.ai/mcp`

## Install

### Claude Code (native platform)

1. **Platform CLI**
```bash
claude mcp add memcell -- npx -y memcell
```

2. **Platform CLI: remote server**
```bash
claude mcp add --transport http memcell https://memcell.ai/mcp
```

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add memcell --url https://memcell.ai/mcp
```

2. **Platform CLI**
```bash
codex mcp add memcell -- npx -y memcell
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "memcell": {
            "url": "https://memcell.ai/mcp"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "memcell": {
            "command": "npx",
            "args": [
                "-y",
                "memcell"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "memcell": {
            "type": "http",
            "url": "https://memcell.ai/mcp"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "memcell": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "memcell"
            ]
        }
    }
}
```

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http memcell https://memcell.ai/mcp
```

2. **Platform CLI**
```bash
gemini mcp add memcell npx -y memcell
```

## When to use it
- retain user choices and decisions across separate agent sessions
- retrieve past preferences before executing terminal commands
- index local PDF and Markdown docs into grounded search chunks
- track outcome feedback to adjust model confidence metrics

## Example prompts
- Recall our previous decisions regarding database migrations.
- Remember that unit tests must always run with the --coverage flag.
- Ingest the project design doc specification.pdf and search for auth specs.

## Similar
- [supermemory](https://affpapa.org/en/nevibecode/skills/supermemoryai-supermemory.md) — skill · 570 installs
- [memory-systems](https://affpapa.org/en/nevibecode/skills/memory-systems.md) — skill · 413 installs
- [neo4j-document-import-skill](https://affpapa.org/en/nevibecode/skills/neo4j-document-import-skill.md) — skill · 984 installs
- [Knowledge Base Manager](https://affpapa.org/en/nevibecode/skills/knowledge-base-manager.md) — skill · 443 installs
- [veritasgraph](https://affpapa.org/en/nevibecode/mcp/veritasgraph.md) — MCP server · ★ 326 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
