# claude-bridge-mcp

> claude-bridge-mcp — millanrp25-dot-claude-bridge-mcp. Use this tool when you need to securely delegate coding tasks to a local code instance, or require structured code review and testing with version control. It solves problems of remote code execution, testing, and review by providing a secure server for MCP clients like ChatGPT. The tool accepts coding tasks as input and returns structured results, making it ideal for use cases involving collaborative coding, automated testing, and version control.

Canonical page: https://skillsregistry.net/skills/millanrp25-dot-claude-bridge-mcp  
JSON: https://api.skillsregistry.net/v1/skills/millanrp25-dot-claude-bridge-mcp

## Description

An MCP server that lets ChatGPT or any MCP client securely delegate coding tasks to a local Claude Code instance, with git checkpointing, approval gates, and structured results. Supports code review, test running, and rollback via simple tool calls.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dbngko5jp0)
- **Repository:** <https://github.com/millanrp25-dot/claude-bridge-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "millanrp25-dot-claude-bridge-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/millanrp25-dot-claude-bridge-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/millanrp25-dot-claude-bridge-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt