# Nimrod

Filters Google results with quality scores and converts webpages into markdown. Helps AI agents fetch clean evidence without drowning in web boilerplate.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 258
- Author: mixelpixx
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mixelpixx/Nimrod
- Updated: 2026-10-03
- HTML: https://affpapa.org/en/nevibecode/mcp/nimrod

## What it does

Nimrod provides four tools for automated research: `google_search` with authority ratings and source classification, `extract_webpage_content` for stripping raw HTML down to markdown, `extract_multiple_webpages` for reading up to 5 URLs in parallel, and `research_topic` to run search, deduplication, and extraction in a single step.

You can connect through the hosted endpoint at `https://nimrod.orchis.ai/mcp` or run Nimrod Desktop locally. The desktop build processes page content on your machine, preventing external servers from seeing the text you read. Mac users must clear the gatekeeper attribute using `xattr -d com.apple.quarantine nimrod-desktop-macos` before the first run.

Webpage extraction is free, while search operations consume 1 credit per query. Search requires an account token, though new registrations receive 50 trial credits without entering card details.

## Requirements
- Remote server: `https://nimrod.orchis.ai/mcp`
- Environment variables: `NIMROD_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http nimrod https://nimrod.orchis.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add nimrod --url https://nimrod.orchis.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "nimrod": {
            "url": "https://nimrod.orchis.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "nimrod": {
            "type": "http",
            "url": "https://nimrod.orchis.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http nimrod https://nimrod.orchis.ai/mcp
```

## When to use it
- retrieve Google search results filtered by source authority
- extract article content as markdown without boilerplate
- read up to 5 web pages concurrently
- synthesize research topics across multiple sites in one call

## Example prompts
- Use `google_search` to find recent technical papers on solid-state batteries.
- Extract clean markdown from these three URLs using `extract_multiple_webpages`.
- Run `research_topic` on RISC-V microcontroller developments and summarize findings.

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
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