What is mcp-server-multi-fetch AGENTS.md?

A repository-specific instruction file for the mcp-server-multi-fetch project. It explains the project structure, Python packaging, dependencies, Docker setup, and how the server fetches web pages and converts them to Markdown.

Use it when working on the MCP server, its HTTP fetching and content-conversion logic, packaging, Docker image, command-line entry point, or development tooling.

It gives coding agents the context needed to make changes without guessing how the repository is organized or built. It also records the tools and versions the project expects.

How alexyangjie/mcp-server-multi-fetch configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to alexyangjie/mcp-server-multi-fetch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/alexyangjie/mcp-server-multi-fetch/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/alexyangjie/mcp-server-multi-fetch

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alexyangjie/mcp-server-multi-fetch/agents-md/github.svg)](https://agentmods.dev/instructions/alexyangjie/mcp-server-multi-fetch/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/alexyangjie/mcp-server-multi-fetch/agents-md"><img src="https://agentmods.dev/badge/instructions/alexyangjie/mcp-server-multi-fetch/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/alexyangjie/mcp-server-multi-fetch/agents-md"><img src="https://agentmods.dev/badge/instructions/alexyangjie/mcp-server-multi-fetch/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 863 This file is loaded in full into every session.

When invoked 863 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00863	$0.00863
Opus 5	$0.00432	$0.00432
Sonnet 5	$0.00173	$0.00173
Haiku 4.5	$0.00086	$0.00086

Measured 8d ago against content hash b30f1599eb70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-server-multi-fetch AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mcp-server-multi-fetch CLAUDE.md — 97% identical, 2 lines differ

AGENTS.md · 82 lines

What it actually says

Codex

Project Overview

Name: mcp-server-multi-fetch
Description: A Model Context Protocol (MCP) server providing tools to fetch and convert web content for usage by LLMs.
License: MIT

Repository Structure

LICENSE            # MIT License
pyproject.toml     # PEP 621 project metadata and dependencies
uv.lock            # Locked dependencies for uv dev environment
README.md          # User guide and configuration examples
src/
  mcp_server_multi_fetch/
    __init__.py    # CLI entrypoint (main, serve)
    __main__.py    # Module entry for `python -m mcp_server_fetch`
    server.py      # Core server logic: tool & prompt registration, HTTP fetching, HTML-to-Markdown conversion

Build & Packaging

Build backend: hatchling ([build-system] in pyproject.toml)
Dev dependencies managed with uv and locked in uv.lock (e.g., pyright, ruff)
Docker build: multi-stage, uses ghcr.io/astral-sh/uv, then Python 3.12-slim
Entry point in container: mcp-server-multi-fetch

Dependencies & Frameworks

Python ≥3.10 (3.12 in Docker)
Async HTTP client: httpx
HTML simplification: readabilipy (Readability)
Markdown conversion: markdownify
Robots.txt parsing: protego
JSON schemas & validation: pydantic v2
MCP integration: mcp library (mcp.server, mcp.types, mcp.shared.exceptions)
CLI & concurrency: argparse, asyncio
Linting & type checking (dev): ruff, pyright

Core Components

CLI (src/mcp_server_fetch/__init__.py):
- Parses flags: --user-agent, --ignore-robots-txt, --proxy-url
- Calls serve() (async)
Server (src/mcp_server_fetch/server.py):
- Registers MCP tools & prompts:
- Tool: fetch (Pydantic model Fetch)
- Prompt: fetch
- Tool: fetch_multi (Pydantic model FetchMulti)
- Prompt: fetch_multi
- Tool: search (Pydantic model Search)
- Prompt: search
- Implements:
  - check_may_autonomously_fetch_url(): respects robots.txt or raises McpError
  - fetch_url(): HTTP GET, error handling, choose raw vs. markdown
  - Tool handler (call_tool): enforce schema, fetch content in chunks
  - Prompt handler (get_prompt): user-initiated fetch
- Runs via STDIO server: mcp.server.stdio.stdio_server

Usage

CLI: mcp-server-multi-fetch [--user-agent UA] [--ignore-robots-txt] [--proxy-url PROXY_URL]
Python module: python -m mcp_server_multi_fetch
UVX: uvx mcp-server-multi-fetch

Development Workflow

Install dependencies: uv sync (dev+prod), or pip install .
Lint: ruff src/
Type check: pyright

Notable Conventions & Tips

HTTP timeouts: 30s
Default persona User-Agent vs. Autonomous UA
Chunked fetching via max_length (default 50000) and start_index
McpError used for controlled error signaling over MCP wire
No unit tests included (add as needed)

For the AI Assistant

Refer to this file when:

Exploring or modifying the server logic (server.py)
Updating CLI flags or tooling configuration
Adjusting dependency versions or build settings
Understanding request-handling flow and error semantics

Keep this codex up-to-date with any structural or conceptual changes.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 82 lines · 863 tokens per session scan A b30f1599eb70

Subscribe to this mod's changes

mcp-server-multi-fetch AGENTS.md is an instructions file published in the GitHub repository alexyangjie/mcp-server-multi-fetch (1 stars, last pushed 1y ago), licensed MIT. It adds 863 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-server-multi-fetch: Instructions file for Codex