MCP.so
Sign In

mcp-server-requests

@coucya

Repository

About mcp-server-requests

Web Content Retrieval (full webpage, filtered content, or Markdown-converted), Custom User-Agent, Multi-HTTP Method Support (GET/POST/PUT/DELETE/PATCH), LLM-Controlled Request Headers, LLM-Accessible Response Headers, and more.

#crawler#web#spider#webpage#mcp#requests#fatch#llm#modelcontextprotocol

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-requests": {
      "command": "python",
      "args": [
        "-m",
        "mcp_server_requests"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-server-requests?

An MCP server that provides HTTP request capabilities, enabling LLMs to fetch and process web content. It offers tools for fetching web content, saving it to files, and making generic HTTP requests, with support for content cleaning and markdown conversion.

How to use mcp-server-requests?

Install by cloning the repository and running pip install .. Configure in the MCP client settings by adding the command python -m mcp_server_requests to the mcpServers JSON. The server can also be started directly from the command line with various optional arguments for User‑Agent and root support.

Key features of mcp-server-requests

  • Fetch web content and convert to Markdown.
  • Filter out non‑visual elements (script, style, meta).
  • Save fetched content directly to files (avoids token consumption).
  • Generic HTTP requests with GET, POST, PUT, PATCH, DELETE.
  • Custom or random User‑Agent strings.
  • MCP workspace root support for file operations.

Use cases of mcp-server-requests

  • Fetch a web page and feed its Markdown content into an LLM.
  • Save scraped web content to a file for later analysis.
  • Make API calls with custom headers and body (JSON/text).
  • Retrieve raw HTML for processing outside the LLM context.
  • Use workspace roots to restrict file saving to project directories.

FAQ from mcp-server-requests

How do I install mcp-server-requests?

Clone the repository from GitHub, then run pip install . in the project directory. Python is required.

How can I customize the User-Agent?

Use the --user-agent flag with a custom string, or --random-user-agent to generate a random one optionally constrained by browser and OS.

What content cleaning options does the fetch tool provide

Frequently asked questions

How do I install mcp-server-requests?

Clone the repository from GitHub, then run `pip install .` in the project directory. Python is required.

How can I customize the User-Agent?

Use the `--user-agent` flag with a custom string, or `--random-user-agent` to generate a random one optionally constrained by browser and OS.

Comments

Basic information

Category

AI & Agents

License

MIT

Transports

stdio

Author

coucya

More AI & Agents MCP servers

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

Sphere

dtajitdinov-aris

Open marketplace where AI agents register, publish services, and transact via escrowed contracts. Live at starsphera.com.

Transform MCP

Unstructured

The Unstructured Transform MCP Server connects your ADK agent to Unstructured, a document processing platform that turns raw files into structured, AI-ready data. This integration gives your agent the ability to parse PD

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K