$ loading_
Scan prompt injection and safely fetch webpages for AI agents.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "TrustFetch" MCP server from askskill: Run: claude mcp add --transport http 'io-github-vohlsyr-trustfetch' 'https://trustfetch.duckdns.org/mcp/'
Developers can use it to scan for prompt-injection risk before an AI agent reads external webpages, then safely fetch the content to reduce risk from untrusted sources.
When researchers collect information from public webpages, they can scan for injection first and then pass safer page content to AI for summarization or analysis.
In a multi-tool agent workflow, it fits as a pre-read step for detecting untrusted content issues and safely fetching webpages.
No documentation provided
Check the source repo for usage and examples.
It is an MCP tool that scans untrusted webpages for prompt injection and safely fetches webpage content for AI agents.
It is suitable when AI agents need to read external webpages, forums, or other untrusted content, with a safety check before reading.
The provided information does not include installation steps, runtime requirements, or key configuration. Please see the source repository.
Gives AI agents reliable web fetching with retries, caching, and anti-bot handling.
Scan AI agents for tool-calling vulnerabilities and surface key security risks.
Fetch, crawl, and search the web for AI agents in clean Markdown.
Scrape websites and extract validated structured content for AI agent workflows.
Scan websites or MCP servers and get a signed trust-readiness scorecard.
Give AI agents keyless web access, search, and asset retrieval.