PluginBench
MCP Server
Active

Nimrod Research MCP Server

ai.orchis/nimrod

Quality-scored Google search, webpage extraction, and deep research for AI agents.

RepositoryRegistry

What is the Nimrod Research MCP server?

Nimrod is a web research MCP server that gives Claude four research tools: quality-scored Google search, webpage extraction, multi-page extraction, and deep topic research. It returns ranked evidence as token-efficient markdown instead of raw HTML, with deterministic costs and control over date, site, and language filters.

Nimrod solves the problem of agents getting lost in SEO noise by providing ranked, clean research results. Instead of raw search results, you get quality-scored Google results, extracted webpage content stripped of boilerplate, and multi-source research synthesis—all designed to be token-efficient and deterministic. Use it when your agent needs reliable web research without hallucination or wasted tokens on HTML cruft.

How to install Nimrod Research

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • NIMROD_API_KEY
    required
    secret

    Your Nimrod API key (nmk_…) from https://nimrod.orchis.ai/portal — free 50-credit trial at signup

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "nimrod": {
      "command": "https://github.com/mixelpixx/Nimrod/releases/download/v1.1.1/nimrod.mcpb",
      "args": [],
      "env": {
        "NIMROD_API_KEY": "<YOUR_NIMROD_API_KEY>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • google_search — Organic Google results with quality scores, authority ratings, and source-type classification (1 credit)
  • extract_webpage_content — Convert any URL to clean markdown with boilerplate stripped (free)
  • extract_multiple_webpages — Fetch and extract up to 5 URLs concurrently (free)
  • research_topic — End-to-end research: search, rank, deduplicate, extract, and synthesize in one call (1 credit + 1 per focus area)

Use cases

  • Gather ranked evidence for fact-checking or report writing without SEO spam
  • Extract clean content from multiple sources simultaneously for synthesis tasks
  • Run deep multi-source research on a topic with automatic deduplication and ranking
  • Build research workflows that stay within predictable token and cost budgets
  • Combine live web research with other MCP tools (e.g., EDA, databases) in a single agent

Nimrod Research MCP server FAQ

What makes Nimrod different from letting Claude search the web directly?

Nimrod returns ranked evidence instead of raw search results, strips boilerplate to deliver token-efficient markdown, offers deterministic costs (1 credit per search), and provides quality/authority scoring. This prevents agent runs from getting lost in SEO noise.

Is Nimrod free?

New accounts get a free 50-credit trial with no card required. After that, pricing is credit-based: 1 credit per Google search or deep research call, plus 1 credit per focus area for multi-source research. Webpage extraction is always free.

How do I install Nimrod in Claude Desktop or Cursor?

In Claude Desktop: Settings → Connectors → Add custom connector → paste https://nimrod.orchis.ai/mcp → sign in with email. For Claude Code, use `claude mcp add nimrod --transport http https://nimrod.orchis.ai/mcp --header "Authorization: Bearer nmk_your_key"`. Desktop/Linux users can also download the local `nimrod-desktop` binary from Releases.

Do I need an API key?

Yes. Sign up at nimrod.orchis.ai to get a free trial and API key. For remote connections, you'll pass the key as a Bearer token in the Authorization header.

Can I use Nimrod offline or on my own machine?

Yes. Download the `nimrod-desktop` binary (Windows, macOS, or Linux) from Releases. It runs locally, keeps extracted pages private, and includes six research skills plus a deep-research agent.

What languages and regions does Nimrod support?

You can control date, site, and language filters in your searches. See the docs at nimrod.orchis.ai/docs.html for full parameter details.

README (reference)

Source of truth, from the repository.

<p align="center"> <img src="https://nimrod.orchis.ai/assets/icon.svg" width="96" alt="Nimrod"> </p> <h1 align="center">Nimrod</h1> <p align="center"><b>Web research your agent can actually use.</b><br> Quality-scored Google search, clean webpage extraction, and deep multi-source research for Claude — over the Model Context Protocol.</p> <p align="center"> <a href="https://nimrod.orchis.ai">Website</a> · <a href="https://nimrod.orchis.ai/docs.html">Docs</a> · <a href="https://nimrod.orchis.ai/#pricing">Pricing</a> · <a href="https://nimrod.orchis.ai/portal">Portal</a> </p>

What it is

Nimrod gives Claude four research tools:

ToolWhat it doesCost
google_searchOrganic Google results with quality scores, authority ratings, and source-type classification1 credit
extract_webpage_contentAny URL → clean markdown, boilerplate strippedfree
extract_multiple_webpagesUp to 5 URLs, fetched concurrentlyfree
research_topicSearch → rank → dedupe → extract → synthesis, in one call1 credit + 1 per focus area

Why not just let the model search? Because raw search is where agent runs go to die: Nimrod returns ranked evidence instead of SEO sludge, as token-efficient markdown instead of raw HTML, with deterministic costs (1 credit = 1 search) and date/site/language control.

New accounts start with a free 50-credit trial — no card required.

Get connected

Claude.ai & Claude Desktop (zero install): Settings → Connectors → Add custom connector → paste https://nimrod.orchis.ai/mcp → sign in with your email. Done.

Claude Code (hosted):

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

Nimrod Desktop (full toolkit — recommended for power users): a locally installed MCP server with six research skills, a deep-research agent, and search-coach hooks (Claude Code features). Extraction is free on every plan; on Desktop it also runs on your own machine, so the pages you read stay private. Grab it from Releases:

  • Windows — nimrod.mcpb for Claude Desktop (double-click, paste key), or nimrod-desktop.exe for Claude Code: nimrod-desktop setup, then claude mcp add nimrod -- path\to\nimrod-desktop.exe
  • macOS — nimrod-desktop-macos (universal: Apple Silicon + Intel): chmod +x it, then a one-time xattr -d com.apple.quarantine nimrod-desktop-macos (not yet Apple-signed), then setup and claude mcp add as above
  • Linux — nimrod-desktop-linux: chmod +x, setup, claude mcp add

In the MCP Registry

Nimrod is listed in the official MCP Registry as ai.orchis/nimrod — MCP clients that browse the registry (including VS Code's MCP gallery) can discover and install it from there.

Built to pair

Run Nimrod beside your other MCP tools — like Konnect for KiCAD: live parts data from your EDA workflow, live web research from Nimrod, one agent, no stale training cutoff.

Support

Docs: nimrod.orchis.ai/docs.html · Email: admin@orchis.ai · Terms · Privacy

<sub>The original open-source BYOK server this project grew from is preserved on the <code>historical-oss</code> branch (unmaintained).</sub>

Related MCP servers

AI

ai.ordercore/ordercore-mcp

Commerce backend for AI agents: catalog, prices, inventory, orders, idempotent checkout.

OROrganize with AI logo

Organize with AI

Search photos/videos; manage collections, people and duplicates. Requires paid OwAI Cloud Access.

OROrgGen AI logo

OrgGen AI

Generate org charts, MCD/ERD data models, and C4 architecture diagrams — pilot OrgGen AI via MCP.

View repository →
AIai.orgsdk/mcp logo

ai.orgsdk/mcp

Hosted runtime for persistent agent teams, durable workflows, memory, schedules, and goals.

ZEZeroMind (OrigoZero game engine) logo

ZeroMind (OrigoZero game engine)

Active

Build, run and publish 3D games in the Zero engine from Claude Code, Cursor or Codex, over MCP.

1
TypeScript
View repository →
OROrisu logo

Orisu

Build and run AI image, video and on-brand ad workflows from chat, with brand kits and share links.