mcp-safe-fetch
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-safe-fetch fetch the text from https://example.com"
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-safe-fetch
An injection-aware content fetcher, exposed over the Model Context Protocol.
Agents that read the open web read content nobody on your team wrote. A page or a post can carry a fake closing tag followed by "ignore previous instructions and ...". This server fetches a URL, strips it to text, runs defense-in-depth sanitization, caps the size, and caches the result. It is small on purpose. It is the reference implementation of a set of production hardening field notes, not a framework.
Why it exists
Most MCP servers are written for a demo: one caller, one happy path, no untrusted input, no cost ceiling. In production the failures cluster in three places, and none of them show up on day one:
Untrusted content. A single tag stripper feels safe and is not. Unicode variants and unclosed tags walk straight through one regex.
Cost. An unbounded response body or an oversized context is money spent on noise.
Concurrency. Two tools touching one SQLite file throw
database is locked.
This server answers all three in code you can read in five minutes.
Related MCP server: WebSurfer MCP
What it does
fetch_clean(url, max_chars=2500) returns sanitized, size-capped text plus an audit of
what was done. The defense is order, not cleverness:
strip the injection wrapper by its literal name, first
normalize unicode (NFKC) so homoglyph tags cannot hide
drop script and style bodies, then the generic tag strip
a second net for common instruction-override phrases
It caps input size with a [truncated] marker (if the model has to ignore most of the
input, you are paying for nothing), clamps the per-call cap at the entry to a hard ceiling,
and caches results in SQLite opened with WAL and busy_timeout so overlapping callers
wait instead of crashing.
Install
pip install -e .Run
As a standalone MCP server (stdio):
mcp-safe-fetchRegister it with an MCP client (for example, Claude Code) by pointing the client at the
mcp-safe-fetch command. The server exposes one tool, fetch_clean.
Test
pip install -e ".[dev]"
pytestThe field notes behind it
The reasoning, with the production incidents that motivated each defense, is written up
here: a short essay on MCP hardening (concurrency, prompt injection, cost) and what breaks
after day 30. The sanitizer in src/mcp_safe_fetch/sanitize.py is the exact function from
that write-up.
License
MIT.
Available Tools
1 toolfetch_cleanB
Fetch a URL and return injection-sanitized, size-capped text.
Args: url: an http/https URL to fetch. max_chars: per-fetch character cap (clamped to a hard ceiling).
Returns a dict with the cleaned content and an audit of what was done.
Inputs: url (required), max_chars.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no ambiguity at all. An agent cannot misselect between tools.
With a single tool, naming is trivially consistent. The name 'fetch_clean' follows a clear verb_noun pattern.
One tool feels thin for a server dedicated to fetching content. While the tool is well-defined, the server would benefit from additional tools (e.g., batch fetch, status check) to justify its scope.
The tool covers the core fetch-and-sanitize operation completely for a single URL. Minor gaps exist (e.g., no way to fetch multiple URLs or configure sanitization levels), but the basic use case is fully served.
Maintenance
Related MCP Connectors
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
Fetch public web pages as clean, token-budgeted text for AI agents.
Fetch public HTTP GET responses as text with status, content type and a content hash.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol server that provides web content fetching and conversion capabilities.4434 npm3MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables AI assistants to securely fetch and extract readable text content from web pages through a standardized interface.1MIT
- AlicenseNot gradedqualityDmaintenanceSecurely fetches web content, extracts links and metadata, and downloads files through a sandboxed MCP server without JavaScript execution. Includes prompt-injection detection and comprehensive HTML sanitization for safe web data retrieval.2MIT
- AlicenseAqualityDmaintenanceEfficiently loads, caches, and delivers project file context for AI agents using the Model Context Protocol, reducing multiple file reads to a single call with LRU caching and security validation.324 npmMIT