FRENES

Data platforms · MCP server

Webfetch: MCP server, setup and security

Webfetch is an open-source MCP server that lets an AI agent search, fetch and rank web pages with semantic caching. Its repository has 60 stars and its last commit is from July 23, 2026 and it is licensed under MIT.

Last commit 3 months agoNeeds secrets

What Webfetch does

According to its repository: “Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Webfetch is listed under Data platforms, a category of 39 servers in the directory, where it ranks #12 by stars.

Topics declared by the repository: agents, anthropic, openai, rag, semantic-cache, web-search.

Installing and connecting Webfetch

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.

The registry lists 3 secret variables to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

Points found for Webfetch:

  • Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on April 20, 2026, the firish/webfetch repository has 60 stars and 6 forks, with 0 open issues. It has more stars than 55% of the servers in the directory. Last change 3 months ago. Version published in the registry: 0.1.3 (July 19, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

MCP server chartMCP server chart : 4.4K4.4KGitLab MCP Server (zereight)GitLab MCP Server (zereight) : 2.1K2.1KMCP mermaidMCP mermaid : 646646Dbt MCPDbt MCP : 612612WalkerOS FlowWalkerOS Flow : 347347QuackbackQuackback : 329329Search Console MCPSearch Console MCP : 308308MCP echartsMCP echarts : 270270WebfetchWebfetch : 6060
GitHub stars of the most followed servers in the category (log scale); Webfetch in orange. Checked October 25, 2026.

Verdict

Webfetch is a reasonable choice; check the points below before connecting it.

Strengths

  • Listed in the official MCP registry
  • Permissive licence (MIT)

Limitations

  • Requires an API key or token

Avoid if…

  • You do not want to give credentials to an agent

Frequently asked questions

How do I install Webfetch?

Webfetch is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of firish/webfetch.

Is Webfetch free?

The code is published under the MIT licence and can be used free of charge. It needs an API key: the service it connects to may be paid.

Is Webfetch safe?

Points to watch: secrets. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by firish on GitHub. Check who maintains it before giving it access.

What are the alternatives to Webfetch?

In the same category: MCP server chart, Dbt MCP, GitLab MCP Server (zereight), and WalkerOS Flow. MCP server chart and Dbt MCP score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score