MCP server
Fetch MCP server
The MCP project's reference Fetch server lets AI download a web page and read it as clean text or markdown.
- Official server
- Search and web
At a glance
- Maintained by
- Model Context Protocol (reference server)
- Tools exposed
- 1 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Fetch is one of the reference servers from the Model Context Protocol project, and it is still maintained there. It does one thing: fetch a URL and return its content, converted to markdown so a language model can read it easily. Long pages can be read in parts.
That small capability is surprisingly useful. An assistant can read a page you point it to, summarize a supplier's terms, check what a competitor changed or pull the details from an announcement.
It needs no credentials. The project documentation warns that it can reach local and internal network addresses, which matters on company networks: an assistant could be tricked into requesting an internal page. Run it where internal systems are not reachable, or block private address ranges.
Fetched pages are untrusted content. A page can contain hidden instructions aimed at AI assistants, so the assistant should treat the text as information only and never follow instructions found inside it.
For many teams, Fetch is the first server they install, because it is simple and useful on day one. It pairs well with a search server: search finds the right pages, and Fetch reads them in full.
Use cases
Best business use cases
Summarize a page
Terms review
Announcement details
Docs lookup
Page checks
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read-only web fetching; warning: it can reach local and internal IP addresses.
-
fetchFetches a URL and returns its content as markdown, with max_length, start_index and raw options.
Workflows
Example workflows
Summarize a policy page
-
1
Paste the page address.
-
2
The assistant fetches it as markdown.
-
3
It reads it in parts if it is long.
-
4
It summarizes the key points.
-
5
It quotes the exact passages that matter.
Check a published price
-
1
List the product pages to check.
-
2
The assistant fetches each page.
-
3
It extracts the displayed price.
-
4
It compares with your price list.
-
5
It reports any mismatch.
Prompts
Example prompts
“Fetch this page and summarize the refund policy in five bullet points.”
“Read this documentation page and explain how authentication works.”
“Fetch these three product pages and list the prices shown.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"fetch": {
"command": "uvx",
"args": [
"mcp-server-fetch"
]
}
}
}Claude Code: terminal
claude mcp add fetch -- uvx mcp-server-fetch- Local server: stdio. PyPI: mcp-server-fetch (uvx mcp-server-fetch). Docker: mcp/fetch.
- Needs: None.
Security
Security considerations
-
Internal network access
It can reach local and internal addresses. Block private ranges or run it in isolation.
-
Untrusted content
Treat fetched text as data, never as instructions.
-
Respect site terms
Only fetch pages you are allowed to use.
-
Review actions
Do not let fetched content trigger actions without review.
Related servers
Servers that pair well with it
Brave Search
Brave's official MCP server gives AI live web, news, image, video and local search from Brave's own independent index.
Firecrawl
Firecrawl's official MCP server lets AI scrape, map, crawl and search the web and get clean, AI-ready content back.
Playwright
Microsoft's Playwright MCP server lets AI drive a real browser: open pages, read them, click, type, fill forms and take screenshots.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- AI agents AI that takes actions in your systems, such as qualifying leads or processing requests, with people checking the results.
- API development Well-documented APIs that let your product talk to apps, partners and AI tools reliably.
Solutions
View all solutions- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Price monitoring Collect competitor prices automatically, match them to your products and alert you when something changes.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- AI lead qualification Score, research and route every new inquiry so your team talks to the best leads first.
- Email triage Sort a shared inbox by topic and urgency, pull out the key details and draft replies for a person to send.
Industries
View all industriesGuides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Astra OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use and research.
- DeepSeek V4 Pro DeepSeek's model for demanding reasoning and agent work, with thinking effort levels, tool calling, JSON output and a 1 million token window.
- Grok 4.7 xAI's current flagship for coding, agent tasks and knowledge work, with image input, tool calling, structured outputs, reasoning effort levels and a 500K window.
- Reasoning Models that think through multi-step problems before answering: analysis, planning, math, complex documents and agent work.
Glossary terms
View all glossary terms- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- Natural language processing Natural language processing is the field of AI that deals with understanding and generating human language, in text or speech.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
- Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.
- Artificial intelligence Artificial intelligence is the broad field of building software that performs tasks that normally need human judgment, such as understanding language or images.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It remains in the MCP project's main servers repository.
No.
Take care: it can reach internal addresses. Block private ranges or run it in isolation.