
Security News
Attackers Are Hunting High-Impact Node.js Maintainers in a Coordinated Social Engineering Campaign
Multiple high-impact npm maintainers confirm they have been targeted in the same social engineering campaign that compromised Axios.
@creative-tim/mcp
Advanced tools
MCP server for Creative Tim OpenClaw — lets Claude Code, Cursor, Lovable and other AI tools spawn and control agents
MCP (Model Context Protocol) server for Creative Tim OpenClaw. Lets Claude Code, Cursor, Lovable, and any other MCP-compatible AI tool spawn and control AI agents programmatically.
Adds 9 tools to your AI assistant:
| Tool | Description |
|---|---|
create_agent | Spin up a new OpenClaw AI agent |
list_agents | List all your agents and their status |
get_agent | Check an agent's current status and lifecycle state |
chat | Send a message and get a reply |
install_skill | Add a capability to an agent |
list_skills | See what skills an agent has |
remove_skill | Remove a skill from an agent |
restart_agent | Restart an agent that's in error state — no data loss |
delete_agent | Permanently delete an agent |
sk-ct-... key (shown once)Add to your project's .mcp.json:
{
"mcpServers": {
"creative-tim": {
"command": "npx",
"args": ["-y", "@creative-tim/mcp"],
"env": {
"OPENCLAW_API_KEY": "sk-ct-..."
}
}
}
}
Or add globally via ~/.claude/mcp.json to use across all projects.
Add to ~/.cursor/mcp.json (or your project's .cursor/mcp.json):
{
"mcpServers": {
"creative-tim": {
"command": "npx",
"args": ["-y", "@creative-tim/mcp"],
"env": {
"OPENCLAW_API_KEY": "sk-ct-..."
}
}
}
}
Add to your claude_desktop_config.json:
{
"mcpServers": {
"creative-tim": {
"command": "npx",
"args": ["-y", "@creative-tim/mcp"],
"env": {
"OPENCLAW_API_KEY": "sk-ct-..."
}
}
}
}
Config file location:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json| Variable | Description |
|---|---|
OPENCLAW_API_KEY | Your sk-ct-... API key (required) |
CREATIVE_TIM_API_KEY | Alias for OPENCLAW_API_KEY |
Agents move through the following states. Use get_agent to check status:
| Status | Meaning |
|---|---|
provisioning | Agent is starting up (~60–80s on first create) |
active | Ready to chat |
error | Transient error — use restart_agent to recover |
Once installed, you can ask your AI assistant:
OPENCLAW_API_KEY=sk-ct-... npx @creative-tim/mcp
Or install globally:
npm install -g @creative-tim/mcp
OPENCLAW_API_KEY=sk-ct-... ct-mcp
The MCP server wraps the @creative-tim/agents SDK and exposes its methods as MCP tools over stdio. Your AI assistant calls these tools to manage the full agent lifecycle without leaving the conversation.
Agent provisioning takes ~60–80 seconds on first creation. If a pre-warmed instance is available it takes ~15–20 seconds instead.
Apache-2.0 — Creative Tim
OpenClaw is an independent open-source project and is not affiliated with or endorsed by Creative Tim. OpenClaw is licensed under the MIT License. For more information visit openclaw.ai or the OpenClaw GitHub repository.
FAQs
MCP server for Creative Tim OpenClaw — lets Claude Code, Cursor, Lovable and other AI tools spawn and control agents
We found that @creative-tim/mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 2 open source maintainers collaborating on the project.
Did you know?

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Security News
Multiple high-impact npm maintainers confirm they have been targeted in the same social engineering campaign that compromised Axios.

Security News
Axios compromise traced to social engineering, showing how attacks on maintainers can bypass controls and expose the broader software supply chain.

Security News
Node.js has paused its bug bounty program after funding ended, removing payouts for vulnerability reports but keeping its security process unchanged.