Claude Code as one-shot MCP server to have an agent in your agent.
Claude Code as one-shot MCP server to have an agent in your agent.
Is it safe?
No package registry to scan for CVEs.
No authentication — any process on your machine can connect to this server.
MIT. View license →
Last scanned 0 days ago.
Is it maintained?
Last commit 92 days ago. 1,216 GitHub stars.
Will it work with my client?
Transport: stdio, sse, http. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
How much context will it use?
1 tool. Estimated ~200 tokens of your context window (0.1% of 200K).
What if it doesn't work?
Common issues: JSON syntax errors in config, network or firewall blocking. Setup guide covers troubleshooting. Or check GitHub issues for known problems.
{
"mcpServers": {
"claude-code-mcp": {
"args": [
"-y",
"@anthropic-ai/claude-code"
],
"command": "npx"
}
}
}No automated test available for this server. Check the GitHub README for setup instructions.
claude_codeExecutes a prompt directly using the Claude Code CLI with --dangerously-skip-permissions
Last scanned 7h ago
No known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.