# Nimrod Research [Health: Active]

**Category:** 🔎 Search & Data Extraction  
**Repository:** https://github.com/mixelpixx/Nimrod  
**GitHub Stars:** 256  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/nimrod-research

## Description
Web research for agents: quality-scored Google search, webpage extraction, and deep research.

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "nimrod-research": {
    "url": "https://nimrod.orchis.ai/mcp"
  }
}
```

## Documentation

## What Nimrod Research MCP server does

Nimrod Research MCP server provides web-research operations through the Model Context Protocol. It connects an MCP client to Google search and web pages, returning structured search evidence or cleaned page content for use by an agent. The service is aimed at research tasks that need current sources, source ranking, and text that is more compact than raw HTML.

Four tools are documented:

- `google_search` returns organic Google results with quality scores, authority ratings, and source-type labels.
- `extract_webpage_content` converts one URL into Markdown after removing page boilerplate.
- `extract_multiple_webpages` processes as many as five URLs concurrently.
- `research_topic` combines search, ranking, deduplication, page extraction, and synthesis in one request.

Search costs one credit. Topic research costs one credit for the search plus one credit for each focus area. Webpage extraction is free. New accounts include a 50-credit trial without requiring a payment card.

## How it works

A hosted MCP endpoint is available at `https://nimrod.orchis.ai/mcp`. Claude.ai and Claude Desktop can connect through the custom connector settings and an email sign-in. Claude Code can use the same endpoint over HTTP with a Nimrod bearer key.

Nimrod Research MCP server can also run through desktop downloads. The README describes a Claude Desktop package for Windows and executable desktop builds for Windows, macOS, and Linux that can be configured for Claude Code. In that local setup, extraction runs on the user’s machine, so pages read through the desktop tool remain private according to the project’s documentation.

The project is also published in the official MCP Registry under `ai.orchis/nimrod`, allowing registry-aware clients such as VS Code’s MCP gallery to discover and install it.

## Setup and configuration

For Claude.ai or Claude Desktop, open Settings, choose Connectors, select Add custom connector, enter the hosted MCP URL, and authenticate with an email address.

For Claude Code, add the hosted server with an HTTP transport and an authorization header containing a Nimrod key:

```bash
claude mcp add nimrod --transport http https://nimrod.orchis.ai/mcp \
  --header "Authorization: Bearer nmk_your_key"
```

Desktop installation differs by platform. Windows provides an `.mcpb` package for Claude Desktop and a desktop executable for Claude Code. The macOS binary is universal but requires executable permission and removal of its quarantine attribute before setup. Linux also requires making the downloaded binary executable before running setup. The README does not specify environment variables.

## Tools and capabilities

The search tool supports date, site, and language control, in addition to quality and authority information. Single-page extraction is useful when an agent already has a URL; concurrent extraction handles a small group of known sources. Topic research is the higher-level option when the agent should discover, filter, read, and synthesize sources in one call.

## Limitations and notes

Search and topic research consume credits, while extraction does not. Topic-research cost varies with the number of focus areas. The hosted Claude Code example requires a bearer key, and the desktop macOS binary is not Apple-signed. The original open-source BYOK implementation remains on a historical branch marked unmaintained.

_Full upstream README: https://allmcps.com/mcp/nimrod-research/readme_