mcp-server-fetch-rag
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-fetch-rag fetch https://en.wikipedia.org/wiki/RAG and explain the main concept"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server Fetch RAG
A Model Context Protocol (MCP) server that fetches web content and returns relevant chunks using RAG (Retrieval-Augmented Generation).
GitHub: https://github.com/attamari/mcp-server-fetch-rag
Features
Semantic Chunking: Groups sentences into coherent chunks based on embedding similarity
Query-based Scoring: Late Interaction with Power Mean aggregation for precise relevance scoring
LexRank Scoring: Graph-based centrality scoring when no query is provided
LexRank Backfill: Supplements query results with high-centrality chunks when needed
Percentile Filtering: Dynamic threshold based on score distribution
Multilingual Support: Uses
paraphrase-multilingual-MiniLM-L12-v2(50+ languages)PDF Support: Extracts text from PDF documents
GPU Acceleration: Auto-detects CUDA, DirectML, ROCm, OpenVINO providers
Context Efficient: Filters out irrelevant content to reduce token usage
Related MCP server: Driflyte MCP Server
Usage
MCP Client Configuration
Add to your MCP client configuration (e.g. claude_desktop_config.json):
{
"mcpServers": {
"fetch-rag": {
"command": "uvx",
"args": [
"--from", "git+https://github.com/attamari/mcp-server-fetch-rag",
"mcp-server-fetch-rag"
]
}
}
}With CLI options:
{
"mcpServers": {
"fetch-rag": {
"command": "uvx",
"args": [
"--from", "git+https://github.com/attamari/mcp-server-fetch-rag",
"mcp-server-fetch-rag",
"--ignore-robots-txt",
"--user-agent", "your-custom-user-agent"
]
}
}
}CLI Options
Option | Description |
| Custom User-Agent string (overrides default MCP UA) |
| Ignore robots.txt restrictions |
| Proxy URL for HTTP requests |
Tool: fetch_rag
Fetches a URL and returns relevant content chunks.
Parameter | Type | Required | Default | Description |
| string | Yes | - | URL to fetch |
| string | No | null | Search query for relevance filtering |
| int | No | 10 | Maximum number of chunks to return |
How It Works
Fetch: Downloads content from URL (HTML via trafilatura, PDF via pypdfium2)
Split: Segments text into sentences using wtpsplit (sat-3l-sm, 85+ languages)
Embed: Generates L2-normalized embeddings (paraphrase-multilingual-MiniLM-L12-v2 via FastEmbed/ONNX)
Chunk: Groups adjacent sentences by embedding similarity into semantic chunks
Score:
With query: Late Interaction — sentence-level query similarity aggregated via Power Mean
Without query: LexRank — sentence-level graph centrality aggregated via Power Mean
Filter: Applies percentile-based dynamic threshold (P30)
Backfill: When query scoring yields insufficient chunks, supplements with high-centrality LexRank chunks (P30 filtered)
Return: Top chunks sorted in original document order
License
MIT License — See LICENSE for details.
Available Tools
1 toolfetch_ragA
Fetch URL and return relevant content. Optionally provide a query to find specific information.
Inputs: url (required), query, max_chunks.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The single tool 'fetch_rag' is distinct by default.
The single tool name follows a clear verb_noun pattern ('fetch_rag'). Consistency is trivially achieved with only one name.
The server contains only one tool, which falls into the borderline category for scope. While a single-purpose fetch/retrieve tool might be acceptable, it feels thin for a typical MCP server.
The tool covers a single operation: fetching a URL and optionally querying for specific information. There are potential gaps such as batch fetching or handling stateful RAG workflows, but for a basic use case it may suffice.
Related MCP Connectors
Convert PDF URLs to clean text or LLM-ready Markdown, with RAG chunks and OCR in 100+ languages.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Search the web and extract clean, readable text from webpages. Process multiple URLs at once to sp…
Fetch any URL and get clean Markdown. Web scraping for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables fetching and processing web content with advanced features including batch processing of up to 20 URLs, streaming support, metadata extraction, and multiple output formats (HTML, Markdown, plain text) with enterprise-grade security and global edge performance.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to query and retrieve topic-specific knowledge from recursively crawled and indexed web pages.297 npm11MIT
- AlicenseNot gradedqualityDmaintenanceFetches web pages and converts them to markdown for LLM consumption, supporting chunked reading and raw content extraction.MIT
- AlicenseNot gradedqualityDmaintenanceProvides AI agents and assistants with advanced web crawling and RAG capabilities, enabling them to scrape websites and perform semantic search over crawled content.1MIT