How do I install MemCell?

Copy the http config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does MemCell need an API key?

No required environment variable is listed on this record.

When was MemCell last checked?

Last checked 2026-10-19. Shared, persistent memory for AI agents: recall before acting, report outcomes to earn confidence.

MemCell MCP server

Power your agent

Add this server

The publisher's own URL. Not a PlugMCP endpoint.

Add to Cursor Add in Claude Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Server URL

https://memcell.ai/mcp

The Claude button above opens Claude with the name and URL filled in. You still confirm it there.

shClaude Code

1claude mcp add --transport http ai.memcell-memcell https://memcell.ai/mcp

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "ai.memcell-memcell": {4      "command": "npx",5      "args": [6        "-y",7        "mcp-remote",8        "https://memcell.ai/mcp"9      ]10    }11  }12}

claude_desktop_config.json

Remote · HTTPPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Remote

Transport: http
Version: 2.2.1
Last checked

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

# Install globally
npm install -g memcell

# In any project:
memcell connect

Run it in any project. memcell connect automatically:

Approves in 1 tap: Opens browser approval (no upfront account needed; guest memories carry over seamlessly on sign-in).
Auto-detects agents: Wires Claude Code, Cursor, Copilot CLI, Gemini CLI, OpenAI Codex, OpenCode, Cline, Windsurf, and more with non-destructive lifecycle hooks and the local stdio MCP server (memcell mcp).
Secures credentials: Stores scoped agent keys directly in your OS keyring (Keychain / Secret Service / Credential Manager).
Creates .memcell: Adds a clean, git-safe project descriptor to your repo root.

Verify anytime:

memcell status

Why MemCell?

Every time you start a new session with an AI agent, it starts with complete amnesia. It falls into the same traps, repeats outdated assumptions, and recreates issues you already resolved yesterday.

Static instruction files and monolithic system prompts don't solve this:

Context Bloat: Stacking dozens of instructions wastes tokens on every turn and dilutes model attention.
Zero Adaptability: Outdated instructions keep firing even when requirements change.
Manual Overhead: You remain the sole feedback loop, constantly hand-editing markdown files.

MemCell gives your agents closed-loop memory:

Pre-Action Recall — Before taking action, agents receive verified memories relevant to the current task.
Execution & Feedback — When actions succeed or fail, real outcomes are reported back.
Earned Confidence — Memories that work gain confidence; memories that fail decay. Zero manual prompt maintenance.

How It Works

MemCell pairs two lightweight layers so agents stay aligned without getting in your way:

Deterministic Hooks (Zero-Touch): Fire automatically on session start, prompt submit, and turn end. Relevant memories and directives are checked before actions begin—without relying on the model remembering to call a tool. Hooks fail open in <50ms, so offline or slow networks never block your editor.
MCP Tool Bridge (memcell mcp): Provides interactive tools (recall, remember, report, ingest) when agents need to search memory or record discoveries mid-turn.

Everyday Usage

Once connected, agents recall and report memory automatically. You can also interact with memory directly from your terminal:

1. Recall Verified Context Before Implementing

memcell recall "how do we handle multi-tenant database sessions?"

2. Record a Decision or Convention

# Record a project convention
memcell remember "Always use pnpm for package operations; never invoke npm directly"

# Bind an invariant to a specific lifecycle trigger
memcell remember "Check database migrations for column locks before altering tables" --at "before db:migrate"

3. Report What Happened

Memories sharpen when told what happened. When an approach succeeds or fails, report the outcome:

memcell report stmt_019a4b2c worked --note "CI suite passed cleanly"
memcell report stmt_019a4b2c failed --note "broke Next.js 15 async cookies"

4. Ingest Specs and Existing Guidelines

# Ingest an architecture doc, spec, or post-mortem
memcell ingest docs/architecture/auth.md

# Scan and import existing guideline files (CLAUDE.md, etc.)
memcell import

5. Check Attributed Token Savings

memcell stats

Displays memories followed, errors avoided, estimated tokens saved from prevented error loops, and 30-day activity sparklines.

Supported Agents & IDEs

Agent / Harness	Integration	How It Runs
Claude Code	Hooks + MCP + Plugin	Automatic lifecycle hooks or marketplace plugin (`/plugin marketplace add memcell-ai/cli`)
Cursor	Hooks + MCP Bridge	Native lifecycle hooks in `.cursor/hooks.json` and stdio bridge in `.cursor/mcp.json`
Gemini CLI	Hooks + MCP	Session and prompt hooks via native CLI harness
GitHub Copilot CLI	Lifecycle Hooks	Pre-command validation hooks
OpenAI Codex / OpenCode	Hooks + MCP	Project descriptor hooks and stdio tools
Cline & Windsurf	MCP Bridge	Native editor MCP client configuration
Factory Droid, Devin, Kiro, Goose	Hooks + MCP	Workspace adapters and tool harnesses

Command Cheat Sheet

Command	Description
`memcell connect`	Connect this directory to MemCell, install hooks, and configure MCP
`memcell status`	Check authentication standing, active project, and connection health
`memcell stats`	Show memories followed, errors avoided, and token savings
`memcell recall <intent>`	Query memory for verified memories and past outcomes before acting
`memcell remember <text>`	File a project convention or directive (`--at` for lifecycle triggers)
`memcell report <id> <outcome>`	Report `worked`, `failed`, or `avoided` to update confidence
`memcell ingest <file>`	Distill a document or specification into atomic memories
`memcell import [files...]`	Import existing guideline files (`CLAUDE.md`, etc.)
`memcell export`	Export project memories as a portable document (`--format json\|md`)
`memcell orgs`	List or switch active organization (`memcell orgs switch <slug>`)
`memcell projects`	List or switch active project (`memcell projects use <slug>`)
`memcell hook remove`	Cleanly remove all MemCell hooks from this directory
`memcell reset`	Clear all cached credentials, keys, and tokens on this machine

Run memcell --help or memcell <command> --help for full flag details.

Clean Uninstall

To remove MemCell hooks from a repository without touching your code:

memcell hook remove
rm .memcell

To remove all stored keys and credentials from your local machine:

memcell reset

MemCell

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install MemCell?

Does MemCell need an API key?

What transport does MemCell use?

When was MemCell last checked?

Documentation

Why MemCell?

How It Works

Everyday Usage

1. Recall Verified Context Before Implementing

2. Record a Decision or Convention

3. Report What Happened

4. Ingest Specs and Existing Guidelines

5. Check Attributed Token Savings

Supported Agents & IDEs

Command Cheat Sheet

Clean Uninstall

Links