with one click
claude-code-mcp-bridge
Run Claude Code as a one-shot MCP tool so other agents and editors can delegate coding tasks to it. An agent-in-agent orchestration bridge.
Menu
Run Claude Code as a one-shot MCP tool so other agents and editors can delegate coding tasks to it. An agent-in-agent orchestration bridge.
| name | Claude Code MCP Bridge |
| slug | claude-code-mcp-bridge |
| description | Run Claude Code as a one-shot MCP tool so other agents and editors can delegate coding tasks to it. An agent-in-agent orchestration bridge. |
| github_stars | 1290 |
| verification | security_reviewed |
| source | https://github.com/steipete/claude-code-mcp |
| author | Peter Steinberger |
| publisher_type | individual |
| category | Developer Tools |
| framework | Claude Code |
| tool_ecosystem | {"github_repo":"steipete/claude-code-mcp","github_stars":1290,"npm_package":"@steipete/claude-code-mcp","npm_weekly_downloads":414} |
Run Claude Code as a one-shot MCP tool so other agents and editors can delegate coding tasks to it. An agent-in-agent orchestration bridge.
Claude Code CLI (installed and authenticated), Node.js v20+, MCP-compatible client
Use the upstream install or setup path that matches your environment:
Requirements and caveats from upstream:
Basic usage or getting-started notes:
Run Claude Code with all permissions bypassed by default (using --dangerously-skip-permissions)
This server is a thin MCP wrapper around the local Claude Code CLI. By default it preserves the historic behavior and starts Claude Code with --dangerously-skip-permissions. Set the tool's permissionMode argument to d...
The wrapper cannot approve prompts that belong to a parent MCP client, bypass macOS privacy prompts, or make another Claude Code session inherit its settings. If the calling client stalls while waiting for permission...
Extracted from upstream docs: https://raw.githubusercontent.com/steipete/claude-code-mcp/HEAD/README.md
Interactive browser skill for logged-in flows, dynamic pages, and session-aware site operations.
""
""
""
Add sandboxed code execution to any MCP-compatible AI client. E2B gives agents access to secure, internet-connected Linux environments for running Python, JavaScript, and shell commands without touching your local machine.
""