# gread

A remote MCP server and skill that let a coding agent read the source of public GitHub repos, docs repos included.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 65
- Author: NitroRCr
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/NitroRCr/gread
- Updated: 2026-07-05
- HTML: https://affpapa.org/en/nevibecode/mcp/gread

## What it does

gread gives an agent the source code behind any public GitHub repository. Ask how a library works and it goes to the implementation instead of recalling the docs from memory.

Nothing runs locally: it is a hosted endpoint at `https://api.gread.dev/mcp` over streamable HTTP, so a single config line does the job. Coding agents can take the skill route instead, installed with `npx skills add https://github.com/NitroRCr/gread --skill gread`. Both routes ship together and you choose one.

Public repos only, so closed company code stays out of reach. When a project keeps its documentation in a separate repository, gread recognises it and serves that repo next to the main one.

## Requirements
- Remote server: `https://api.gread.dev/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http gread https://api.gread.dev/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add gread --url https://api.gread.dev/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "gread": {
            "url": "https://api.gread.dev/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "gread": {
            "type": "http",
            "url": "https://api.gread.dev/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http gread https://api.gread.dev/mcp
```

## When to use it
- Trace how a third-party library actually implements a function
- Find which module in a repo holds a given piece of logic
- Pull a project's docs repo together with its source
- Check an API's behaviour before adding the dependency
- Settle a docs-versus-code mismatch from the implementation

## Example prompts
- Open the source of the library listed in my `package.json` and show me where it parses the config.
- Find this project's docs repo and compare the API it describes with the code.
- Read `.agents/skills/gread/SKILL.md` and tell me which queries you can run through gread.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md