mrkrsl/web-search-mcp

Score: 26.0 Rank #8379

A simple, locally hosted Web Search MCP server for use with Local LLMs

Overview

mrkrsl/web-search-mcp is a TypeScript MCP server licensed under MIT. A simple, locally hosted Web Search MCP server for use with Local LLMs Topics: llm, lmstudio, local-llm, mcp, web-search.

Ranked #8379 out of 25632 indexed tools.

Ecosystem

TypeScript MIT

llmlmstudiolocal-llmmcpweb-search

Signal Breakdown

Stars 632

Freshness 7mo ago

Issue Health 19%

Contributors 2

Dependents 0

Forks 90

Description Good

License MIT

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 219 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 22 open vs 5 closed issues — triaging stale issues improves health

Badge

AgentRank score for mrkrsl/web-search-mcp

Markdown

[![AgentRank](https://agentrank-ai.com/api/badge/tool/mrkrsl--web-search-mcp)](https://agentrank-ai.com/tool/mrkrsl--web-search-mcp)

HTML

<a href="https://agentrank-ai.com/tool/mrkrsl--web-search-mcp"><img src="https://agentrank-ai.com/api/badge/tool/mrkrsl--web-search-mcp" alt="AgentRank"></a>

Details

Stars: 632
Forks: 90
Open Issues: 22
Closed Issues: 5
Contributors: 2
Dependents: —
Language: TypeScript
License: MIT
Last Commit: 7mo ago

Matched Queries

"mcp server""mcp-server"

From the README

# Web Search MCP Server for use with Local LLMs

A TypeScript MCP (Model Context Protocol) server that provides comprehensive web search capabilities using direct connections (no API keys required) with multiple tools for different use cases.

## Features

- **Multi-Engine Web Search**: Prioritises Bing > Brave > DuckDuckGo for optimal reliability and performance
- **Full Page Content Extraction**: Fetches and extracts complete page content from search results
- **Multiple Search Tools**: Three specialised tools for different use cases
- **Smart Request Strategy**: Switches between playwright browesrs and fast axios requests to ensure results are returned
- **Concurrent Processing**: Extracts content from multiple pages simultaneously

## How It Works

The server provides three specialised tools for different web search needs:

### 1. `full-web-search` (Main Tool)
When a comprehensive search is requested, the server uses an **optimised search strategy**:
1. **Browser-based Bing Search*

Read full README on GitHub →

View on GitHub →

Are you the maintainer? Claim this listing