hshintelligence-agentscrape
mcpsmithery**Pay-per-call web scraping for AI agents — no signup, no API keys, just USDC.** AgentScrape is a production MCP server giving agents six paid tools for web scraping, structured extraction, screenshots, and metadata — all on Cloudflare Workers, all settled in USDC on Base via x402. ## Tools - **`scrape_webpage`** — fetch as markdown, html, text, or json - **`extract_structured_data`** — AI-powered extraction with natural-language prompts + JSON schemas - **`screenshot_webpage`** — PNG capture, viewport configurable - **`extract_metadata`** — OG, Twitter Card, JSON-LD - **`create_browser_session`** — persistent sessions for multi-step flows - **`run_workflow`** — multi-step atomic execution ## Pricing $0.001–$0.008 USDC per call on Base mainnet. No subscriptions. No API keys. Pay per request via x402. **Free tier:** 10 calls per wallet per 30 days. No signup required. ## Stack Cloudflare Workers · Hono · `@x402/hono` v2 · MCP Streamable HTTP · xpay.sh facilitator · Browser Rendering MIT licensed. Built by HSH Intelligence.
By Smithery | 17 findings | Scanned 7/5/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Safe With Normal ControlsExcessive Permissions is the main signal, but overall risk remains within an acceptable range.
Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (17)
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
scrape_webpageextract_structured_datascreenshot_webpageextract_metadatarun_workflowFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
declared capabilities: network access
scrape_webpageextract_structured_datascreenshot_webpageextract_metadatadeclared capabilities: filesystem access
create_browser_sessiondeclared capabilities: code/command execution
run_workflowFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
scrape_webpageextract_structured_datascreenshot_webpageextract_metadatacreate_browser_sessionrun_workflowFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y hshintelligence-agentscrape"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)