Nimrod
Web search with quality scores; web pages are read on your computer by the local server.
- GitHub stars
- 260
- tools
- 4
- auth
- Secret needed
- transport
- STDIO, HTTP
- env var
- 1
- last updated
- Oct 2, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
google_searchOrganic Google results with quality scores, authority ratings, and source-type classification
Organic Google results with quality scores, authority ratings, and source-type classification
No parameter schema in public metadata yet.
extract_webpage_contentAny URL → clean markdown, boilerplate stripped
Any URL → clean markdown, boilerplate stripped
No parameter schema in public metadata yet.
extract_multiple_webpagesUp to 5 URLs, fetched concurrently
Up to 5 URLs, fetched concurrently
No parameter schema in public metadata yet.
research_topicSearch → rank → dedupe → extract → synthesis, in one call
Search → rank → dedupe → extract → synthesis, in one call
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
NIMROD_API_KEYsecretOptional. Leave unset to sign in with your browser on the first search; or an nmk_ key from https://nimrod.orchis.ai/portal
Readme
Nimrod
Web research your agent can actually use.
Quality-scored Google search, clean webpage extraction, and deep multi-source
research for Claude — over the Model Context Protocol.
Website · Docs · Pricing · Portal
What it is
Nimrod gives Claude four research tools:
| Tool | What it does | Cost |
|---|---|---|
google_search | Organic Google results with quality scores, authority ratings, and source-type classification | 1 credit |
extract_webpage_content | Any URL → clean markdown, boilerplate stripped | free |
extract_multiple_webpages | Up to 5 URLs, fetched concurrently | free |
research_topic | Search → rank → dedupe → extract → synthesis, in one call | 1 credit + 1 per focus area |
Details
- Repository
- github.com/mixelpixx/nimrod
- Website
- nimrod.orchis.ai
- Category
- Search & Web Crawling
- Package
https://github.com/mixelpixx/Nimrod/releases/download/v2.1.0/nimrod.mcpb- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active
More from mixelpixx
Related Search & Web Crawling MCP servers
View all
UI Beatsnikhils4/ui-beatsMCP server for UI Beats. Let your coding agent search, read and install animated React components.235stars
Photoshoploonghao/photoshop-python-api-mcp-serverProvides a bridge between MCP and Adobe Photoshop to create documents, manage layers, apply effects, and fetch session information on Windows.223stars
GSCahonn/mcp-server-gscProvides access to Google Search Console data with enhanced analytics and filtering capabilities.219stars
Shodh Memoryvarun29ankus/shodh-memoryCognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.217stars
Bitbybit CAD MCPbitbybit-dev/bitbybitBitbybit 3D parametric CAD API, version-exact, for coding agents: search, describe, examples, guide211stars
Bilibili APIhuccihuang/bilibili-mcp-serverProvides an MCP server for Bilibili API with general search, user search, precise results, and danmaku retrieval.185stars