MCP server/cloud

0pi MCP Server

Ephemeral shared workspace for caching contexts and bridging multi-agent workflows

dizzydes/0pi-mcp-server ↗by dizzydesupdated
1

Add it to Claude Code

claude mcp add 0pi-mcp-server -- npx @0pi/mcp-server
2

Make your agent remember this setup

0pi-mcp-server's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.

npx conare@latest

Free · one command · indexes the sessions already on disk. Set up in the browser instead →

What it does

  • Create shared workspaces for JSON structures, reasoning states, or DOM elements
  • Retrieve previously saved data via unique workspace ID
  • Ephemeral storage with 2-hour auto-expiry
  • Local JSONL logging for all MCP interactions

Tools 2

create_shared_workspaceSave data to an ephemeral cloud workspace.
get_shared_workspaceRetrieve data from a workspace.

Environment Variables

0PI_API_URLAPI endpoint URL (default: https://0pi.dev)
0PI_LOG_DIRDirectory for log files (default: ./logs)

Try it

Save my current research findings to a shared workspace so I can access them in a different agent session.
Retrieve the workspace with ID a8f92k3d to continue working on the project.
Create a shared workspace for my current DOM snapshot with a TTL of 3600 seconds.
Store these intermediate code results in a temporary workspace for my next agent task.
Original README from dizzydes/0pi-mcp-server

0pi MCP Server

Dropbox for AI Agents - Ephemeral shared workspace for caching contexts and bridging multi-agent workflows

A Model Context Protocol (MCP) server that enables AI agents to cache contexts, bridge workflows, and share ephemeral data via the 0pi free and open API. Think of it like a pastebin or Dropbox for Agents.

Use Cases

🧠 Context Caching - Offload large contexts when approaching token limits
🤝 Multi-Agent Bridge - Share data between different AI agents seamlessly
📦 Temporary Storage - 2-hour auto-expiring storage for agent content
🔄 Workflow Continuity - Pass intermediate results between sessions
🌐 Web Automation - Store DOM snapshots for multi-step workflows
💾 Code Sharing - Temporary storage for generated code

Features

  • Create Shared Workspaces: Save large JSON structures, reasoning states, or DOM elements to the cloud
  • Retrieve Workspaces: Access previously saved data via workspace ID
  • JSONL Logging: All MCP interactions are logged locally in JSON Lines format for debugging and analytics
  • Ephemeral Storage: All data expires after 2 hours (configurable)

Installation

As a Local MCP Server

  1. Install dependencies:
cd mcp-server
npm install
  1. Configure environment (optional):
cp .env.example .env
# Edit .env to set 0PI_API_URL if needed
  1. Run the server:
npm start

Install via NPM

npm install -g @0pi/mcp-server
# or use npx
npx @0pi/mcp-server

Configuration with AI Tools

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "0pi": {
      "command": "npx",
      "args": ["@0pi/mcp-server"],
      "env": {
        "0PI_API_URL": "https://0pi.dev"
      }
    }
  }
}

Cline (VS Code)

Add to your Cline MCP settings:

{
  "mcpServers": {
    "0pi": {
      "command": "npx",
      "args": ["@0pi/mcp-server"],
      "env": {
        "0PI_API_URL": "https://0pi.dev"
      }
    }
  }
}

Available Tools

1. `create_shared_workspace`

Save data to an ephemeral cloud workspace.

Parameters:

  • agent_id (required): Your agent identifier (e.g., "claude-coder")
  • data (required): The payload to save (object, array, or string)
  • intent (optional): Brief description of why you're saving this
  • ttl_seconds (optional): Time-to-live in seconds (max 7200, default 7200)

Example:

{
  "agent_id": "claude-researcher",
  "data": {
    "research_findings": [...],
    "next_steps": [...]
  },
  "intent": "Saving research results for coding agent",
  "ttl_seconds": 3600
}

Returns:

{
  "workspace_id": "a8f92k3d",
  "url": "https://0pi.dev/w/a8f92k3d",
  "expires_in": 3600
}

2. `get_shared_workspace`

Retrieve data from a workspace.

Parameters:

  • workspace_id (required): The 8-character workspace ID

Example:

{
  "workspace_id": "a8f92k3d"
}

Returns:

{
  "agent_id": "claude-researcher",
  "payload_type": "json",
  "data": { ... },
  "intent": "Saving research results for coding agent",
  "created_at": "2026-05-03T13:57:56Z"
}

JSONL Logging

All MCP interactions are logged to logs/mcp-conversations.jsonl in JSON Lines format (one JSON object per line).

Log Entry Format:

{
  "timestamp": "2026-05-03T13:57:56.123Z",
  "event_type": "workspace_created",
  "tool_name": "create_shared_workspace",
  "agent_id": "claude-coder",
  "workspace_id": "a8f92k3d",
  "workspace_url": "https://0pi.dev/w/a8f92k3d",
  "payload_size": 15420,
  "intent": "saving DOM structure for handoff",
  "error": null,
  "metadata": null
}

Event Types:

  • server_started: MCP server initialized
  • tools_listed: Agent queried available tools
  • tool_called: Agent invoked a tool
  • workspace_created: Workspace successfully created
  • workspace_creation_failed: Error creating workspace
  • workspace_retrieved: Workspace data retrieved
  • workspace_retrieval_failed: Error retrieving workspace
  • tool_execution_failed: General tool execution error

Analyzing Logs:

# View recent events (last 10 lines)
tail -10 mcp-server/logs/mcp-conversations.jsonl

# View all workspace creations
cat mcp-server/logs/mcp-conversations.jsonl | grep "workspace_created"

# Count events by type using jq
cat mcp-server/logs/mcp-conversations.jsonl | jq -s 'group_by(.event_type) | map({event: .[0].event_type, count: length})'

# View errors only
cat mcp-server/logs/mcp-conversations.jsonl | jq 'select(.error != null)'

# Count workspaces by agent
cat mcp-server/logs/mcp-conversations.jsonl | jq -s 'map(select(.event_type == "workspace_created")) | group_by(.agent_id) | map({agent: .[0].agent_id, count: length})'

Environment Variables

<<<<<<< HEAD

  • 0PI_API_URL: API endpoint URL (default: https://0pi.dev)
    • Legacy: AGENTBOX_API_URL still supported
  • 0PI_LOG_DIR: Directory for log files (default: `./logs

Frequently Asked Questions

What are the key features of 0pi MCP Server?

Create shared workspaces for JSON structures, reasoning states, or DOM elements. Retrieve previously saved data via unique workspace ID. Ephemeral storage with 2-hour auto-expiry. Local JSONL logging for all MCP interactions.

What can I use 0pi MCP Server for?

Offloading large contexts when approaching token limits. Sharing data between different AI agents seamlessly. Passing intermediate results between different AI sessions. Storing DOM snapshots for multi-step web automation workflows.

How do I install 0pi MCP Server?

Install 0pi MCP Server by running: npm install -g @0pi/mcp-server

What MCP clients work with 0pi MCP Server?

0pi MCP Server works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Conare · memory for coding agents

Turn this server into reusable context

Keep 0pi MCP Server docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Set up free$npx conare@latest